Initial commit of Pyramids RND.

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208994d86cf6bc899604a079ff16e4c16687f999ebe4b1c7c3684dd5eb13549a
+size 1418184

Pyramids/Pyramids-1000014.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208994d86cf6bc899604a079ff16e4c16687f999ebe4b1c7c3684dd5eb13549a
+size 1418184

Pyramids/Pyramids-1000014.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7a8ef27b968f7ad48bf2300a9ab7ec4beb41a0fbbd9b205e35b8c9ff5b8a83
+size 8650990

Pyramids/Pyramids-499981.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f8ca8d596ce5af3ad17e7f597d269320a1c25768602aa3747d5d8e1f9012df0
+size 1418184

Pyramids/Pyramids-499981.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f53ff7a23b602ec442afe6d869985d05cf2be42c8dde65e36ace7261d916079
+size 8650990

Pyramids/Pyramids-999991.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208994d86cf6bc899604a079ff16e4c16687f999ebe4b1c7c3684dd5eb13549a
+size 1418184

Pyramids/Pyramids-999991.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f311dcf5e6dcc6fe39c6daa732426ca8bcad4db6757c3a2388971e2df8d4860
+size 8650990

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7a8ef27b968f7ad48bf2300a9ab7ec4beb41a0fbbd9b205e35b8c9ff5b8a83
+size 8650990

Pyramids/events.out.tfevents.1685010432.stephen-Vivobook.151553.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b7ba61ce54769bdfdb530d4ba0900fcc298070de868bf134fa6411d8821bb90
+size 323934

README.md

@@ -0,0 +1,29 @@
+---
+library_name: ml-agents
+tags:
+- Pyramids
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-Pyramids
+---
+
+  # **ppo** Agent playing **Pyramids**
+  This is a trained model of a **ppo** agent playing **Pyramids** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+  
+  ## Usage (with ML-Agents)
+  The Documentation: https://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser:**.
+  
+  1. Go to https://huggingface.co/spaces/unity/ML-Agents-Pyramids
+  2. Step 1: Find your model_id: Steddex/ppo-PyramidsTraining
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 1280, "height": 720, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,90 @@
+default_settings: null
+behaviors:
+  Pyramids:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 64
+          num_layers: 3
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 1000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/Pyramids/Pyramids
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 1280
+  height: 720
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: Pyramids Training
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,393 @@
+Mono path[0] = '/home/stephen/Personal/2023-05-24_DeepRL/deep-rl-class/notebooks/unit5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/stephen/Personal/2023-05-24_DeepRL/deep-rl-class/notebooks/unit5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 2 interfaces on host : 0) 172.17.0.1 1) 192.168.1.80
+Multi-casting "[IP] 172.17.0.1 [Port] 55347 [Flags] 2 [Guid] 1644894758 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.1.80) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Display 0 'U28E850 28"': 3840x2160 (primary device).
+Display 1 '1': 3840x2400 (secondary device).
+PlayerPrefs - Creating folder: /home/stephen/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /home/stephen/.config/unity3d/Unity Technologies/UnityEnvironment
+Unable to load player prefs
+Desktop is 3840 x 2160 @ 30 Hz
+Invalid initial resolution 80 x 80 - forcing to 100 x 100
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /home/stephen/Personal/2023-05-24_DeepRL/deep-rl-class/notebooks/unit5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
+GfxDevice: creating device client; threaded=1; jobified=0
+Renderer: AMD RENOIR (DRM 3.42.0, 5.15.0-71-generic, LLVM 12.0.0)
+Vendor:   AMD
+Version:  4.6 (Core Profile) Mesa 21.2.6
+GLES:     0
+ GL_AMD_conservative_depth GL_AMD_depth_clamp_separate GL_AMD_draw_buffers_blend GL_AMD_framebuffer_multisample_advanced GL_AMD_gpu_shader_int64 GL_AMD_multi_draw_indirect GL_AMD_performance_monitor GL_AMD_pinned_memory GL_AMD_query_buffer_object GL_AMD_seamless_cubemap_per_texture GL_AMD_shader_stencil_export GL_AMD_shader_trinary_minmax GL_AMD_texture_texture4 GL_AMD_vertex_shader_layer GL_AMD_vertex_shader_viewport_index GL_ANGLE_texture_compression_dxt3 GL_ANGLE_texture_compression_dxt5 GL_ARB_ES2_compatibility GL_ARB_ES3_1_compatibility GL_ARB_ES3_2_compatibility GL_ARB_ES3_compatibility GL_ARB_arrays_of_arrays GL_ARB_base_instance GL_ARB_bindless_texture GL_ARB_blend_func_extended GL_ARB_buffer_storage GL_ARB_clear_buffer_object GL_ARB_clear_texture GL_ARB_clip_control GL_ARB_color_buffer_float GL_ARB_compressed_texture_pixel_storage GL_ARB_compute_shader GL_ARB_compute_variable_group_size GL_ARB_conditional_render_inverted GL_ARB_conservative_depth GL_ARB_copy_buffer GL_ARB_copy_image GL_ARB_cull_dist
+ance GL_ARB_debug_output GL_ARB_depth_buffer_float GL_ARB_depth_clamp GL_ARB_derivative_control GL_ARB_direct_state_access GL_ARB_draw_buffers GL_ARB_draw_buffers_blend GL_ARB_draw_elements_base_vertex GL_ARB_draw_indirect GL_ARB_draw_instanced GL_ARB_enhanced_layouts GL_ARB_explicit_attrib_location GL_ARB_explicit_uniform_location GL_ARB_fragment_coord_conventions GL_ARB_fragment_layer_viewport GL_ARB_fragment_shader GL_ARB_framebuffer_no_attachments GL_ARB_framebuffer_object GL_ARB_framebuffer_sRGB GL_ARB_get_program_binary GL_ARB_get_texture_sub_image GL_ARB_gl_spirv GL_ARB_gpu_shader5 GL_ARB_gpu_shader_fp64 GL_ARB_gpu_shader_int64 GL_ARB_half_float_pixel GL_ARB_half_float_vertex GL_ARB_indirect_parameters GL_ARB_instanced_arrays GL_ARB_internalformat_query GL_ARB_internalformat_query2 GL_ARB_invalidate_subdata GL_ARB_map_buffer_alignment GL_ARB_map_buffer_range GL_ARB_multi_bind GL_ARB_multi_draw_indirect GL_ARB_occlusion_query2 GL_ARB_parallel_shader_compile GL_ARB_pipeline_statistics_query GL_ARB_pixel
+_buffer_object GL_ARB_point_sprite GL_ARB_polygon_offset_clamp GL_ARB_program_interface_query GL_ARB_provoking_vertex GL_ARB_query_buffer_object GL_ARB_robust_buffer_access_behavior GL_ARB_robustness GL_ARB_sample_shading GL_ARB_sampler_objects GL_ARB_seamless_cube_map GL_ARB_seamless_cubemap_per_texture GL_ARB_separate_shader_objects GL_ARB_shader_atomic_counter_ops GL_ARB_shader_atomic_counters GL_ARB_shader_ballot GL_ARB_shader_bit_encoding GL_ARB_shader_clock GL_ARB_shader_draw_parameters GL_ARB_shader_group_vote GL_ARB_shader_image_load_store GL_ARB_shader_image_size GL_ARB_shader_objects GL_ARB_shader_precision GL_ARB_shader_stencil_export GL_ARB_shader_storage_buffer_object GL_ARB_shader_subroutine GL_ARB_shader_texture_image_samples GL_ARB_shader_texture_lod GL_ARB_shader_viewport_layer_array GL_ARB_shading_language_420pack GL_ARB_shading_language_include GL_ARB_shading_language_packing GL_ARB_sparse_buffer GL_ARB_spirv_extensions GL_ARB_stencil_texturing GL_ARB_sync GL_ARB_tessellation_shader GL_ARB
+_texture_barrier GL_ARB_texture_buffer_object GL_ARB_texture_buffer_object_rgb32 GL_ARB_texture_buffer_range GL_ARB_texture_compression_bptc GL_ARB_texture_compression_rgtc GL_ARB_texture_cube_map_array GL_ARB_texture_filter_anisotropic GL_ARB_texture_float GL_ARB_texture_gather GL_ARB_texture_mirror_clamp_to_edge GL_ARB_texture_multisample GL_ARB_texture_non_power_of_two GL_ARB_texture_query_levels GL_ARB_texture_query_lod GL_ARB_texture_rectangle GL_ARB_texture_rg GL_ARB_texture_rgb10_a2ui GL_ARB_texture_stencil8 GL_ARB_texture_storage GL_ARB_texture_storage_multisample GL_ARB_texture_swizzle GL_ARB_texture_view GL_ARB_timer_query GL_ARB_transform_feedback2 GL_ARB_transform_feedback3 GL_ARB_transform_feedback_instanced GL_ARB_transform_feedback_overflow_query GL_ARB_uniform_buffer_object GL_ARB_vertex_array_bgra GL_ARB_vertex_array_object GL_ARB_vertex_attrib_64bit GL_ARB_vertex_attrib_binding GL_ARB_vertex_buffer_object GL_ARB_vertex_shader GL_ARB_vertex_type_10f_11f_11f_rev GL_ARB_vertex_type_2_10_10_10_
+rev GL_ARB_viewport_array GL_ATI_blend_equation_separate GL_ATI_meminfo GL_ATI_texture_float GL_ATI_texture_mirror_once GL_EXT_EGL_image_storage GL_EXT_EGL_sync GL_EXT_abgr GL_EXT_blend_equation_separate GL_EXT_demote_to_helper_invocation GL_EXT_depth_bounds_test GL_EXT_draw_buffers2 GL_EXT_draw_instanced GL_EXT_framebuffer_blit GL_EXT_framebuffer_multisample GL_EXT_framebuffer_multisample_blit_scaled GL_EXT_framebuffer_object GL_EXT_framebuffer_sRGB GL_EXT_memory_object GL_EXT_memory_object_fd GL_EXT_packed_depth_stencil GL_EXT_packed_float GL_EXT_pixel_buffer_object GL_EXT_polygon_offset_clamp GL_EXT_provoking_vertex GL_EXT_semaphore GL_EXT_semaphore_fd GL_EXT_shader_image_load_formatted GL_EXT_shader_image_load_store GL_EXT_shader_integer_mix GL_EXT_shader_samples_identical GL_EXT_texture_array GL_EXT_texture_compression_dxt1 GL_EXT_texture_compression_rgtc GL_EXT_texture_compression_s3tc GL_EXT_texture_filter_anisotropic GL_EXT_texture_integer GL_EXT_texture_mirror_clamp GL_EXT_texture_sRGB GL_EXT_textur
+e_sRGB_R8 GL_EXT_texture_sRGB_decode GL_EXT_texture_shadow_lod GL_EXT_texture_shared_exponent GL_EXT_texture_snorm GL_EXT_texture_swizzle GL_EXT_timer_query GL_EXT_transform_feedback GL_EXT_vertex_array_bgra GL_EXT_vertex_attrib_64bit GL_EXT_window_rectangles GL_IBM_multimode_draw_arrays GL_INTEL_blackhole_render GL_KHR_blend_equation_advanced GL_KHR_context_flush_control GL_KHR_debug GL_KHR_no_error GL_KHR_parallel_shader_compile GL_KHR_robust_buffer_access_behavior GL_KHR_robustness GL_KHR_texture_compression_astc_ldr GL_KHR_texture_compression_astc_sliced_3d GL_MESA_framebuffer_flip_y GL_MESA_pack_invert GL_MESA_shader_integer_functions GL_MESA_texture_signed_rgba GL_NVX_gpu_memory_info GL_NV_alpha_to_coverage_dither_control GL_NV_compute_shader_derivatives GL_NV_conditional_render GL_NV_copy_image GL_NV_depth_clamp GL_NV_packed_depth_stencil GL_NV_shader_atomic_int64 GL_NV_texture_barrier GL_NV_vdpau_interop GL_OES_EGL_image GL_S3_s3tc
+OPENGL LOG: Creating OpenGL 4.6 graphics device ; Context level  <OpenGL 4.5> ; Context handle 36762384
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.085 seconds
+Default vsync count 1
+requesting resize 80 x 80
+resizing window to 80 x 80
+Desktop is 3840 x 2160 @ 30 Hz
+Desktop is 3840 x 2160 @ 30 Hz
+UnloadTime: 1.400406 ms
+Setting up 8 worker threads for Enlighten.
+requesting resize 1280 x 720
+resizing window to 1280 x 720
+Desktop is 3840 x 2160 @ 30 Hz
+PlayerConnection::CleanupMemory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3909 frames, [32.0 KB-64.0 KB]: 11492 frames, [64.0 KB-128.0 KB]: 3364 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 1.9 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AUDIO_FMOD stream thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 13]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 320.0 KB
+      Peak Allocated Bytes 251.6 KB
+      Overflow Count 4
+    [ALLOC_TEMP_AUDIO_FMOD PulseAudio Mixer]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 15
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 8
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_UnityGfxDeviceWorker]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 45.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 162 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18467 frames
+  Requested Block Size 1.0 MB
+  Peak Block count 2
+  Peak Allocated memory 1.6 MB
+  Peak Large allocation bytes 0 B
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 14825
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 2.3 MB
+      Failed Allocations. Bucket layout:
+        16B: 17 Subsections = 5802 buckets. Failed count: 142216
+        32B: 38 Subsections = 9728 buckets. Failed count: 32754
+        48B: 43 Subsections = 8806 buckets. Failed count: 5252
+        64B: 50 Subsections = 8533 buckets. Failed count: 13959
+        80B: 35 Subsections = 5120 buckets. Failed count: 45758
+        96B: 43 Subsections = 5504 buckets. Failed count: 9185
+        112B: 15 Subsections = 1706 buckets. Failed count: 1431
+        128B: 15 Subsections = 1536 buckets. Failed count: 2711
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 299 frames, [32.0 MB-64.0 MB]: 18467 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 40.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [32.0 MB-64.0 MB]: 18766 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 50.3 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 5
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 1
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 2.3 MB
+      Failed Allocations. Bucket layout:
+        16B: 17 Subsections = 5802 buckets. Failed count: 142216
+        32B: 38 Subsections = 9728 buckets. Failed count: 32754
+        48B: 43 Subsections = 8806 buckets. Failed count: 5252
+        64B: 50 Subsections = 8533 buckets. Failed count: 13959
+        80B: 35 Subsections = 5120 buckets. Failed count: 45758
+        96B: 43 Subsections = 5504 buckets. Failed count: 9185
+        112B: 15 Subsections = 1706 buckets. Failed count: 1431
+        128B: 15 Subsections = 1536 buckets. Failed count: 2711
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18765 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.7 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18766 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 69.7 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 1
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 2.3 MB
+      Failed Allocations. Bucket layout:
+        16B: 17 Subsections = 5802 buckets. Failed count: 142216
+        32B: 38 Subsections = 9728 buckets. Failed count: 32754
+        48B: 43 Subsections = 8806 buckets. Failed count: 5252
+        64B: 50 Subsections = 8533 buckets. Failed count: 13959
+        80B: 35 Subsections = 5120 buckets. Failed count: 45758
+        96B: 43 Subsections = 5504 buckets. Failed count: 9185
+        112B: 15 Subsections = 1706 buckets. Failed count: 1431
+        128B: 15 Subsections = 1536 buckets. Failed count: 2711
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18766 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_CACHEOBJECTS_THREAD]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 18766 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 7.0 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 2.3 MB
+      Failed Allocations. Bucket layout:
+        16B: 17 Subsections = 5802 buckets. Failed count: 142216
+        32B: 38 Subsections = 9728 buckets. Failed count: 32754
+        48B: 43 Subsections = 8806 buckets. Failed count: 5252
+        64B: 50 Subsections = 8533 buckets. Failed count: 13959
+        80B: 35 Subsections = 5120 buckets. Failed count: 45758
+        96B: 43 Subsections = 5504 buckets. Failed count: 9185
+        112B: 15 Subsections = 1706 buckets. Failed count: 1431
+        128B: 15 Subsections = 1536 buckets. Failed count: 2711
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 18766 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.0 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_TYPETREE_THREAD]
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18766 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.9 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_PROFILER]
+  Peak usage frame count: [32.0 KB-64.0 KB]: 18766 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 45.5 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 396 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1685011640191,"processId":151610,"allocatedMemory":3528406,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":1557690},{"Thread":34980},{"Manager":18511},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":67733},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":672},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3671},{"DynamicArray":30872},{"HashMap":7680},{"Utility":7072},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -0,0 +1,398 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.3839273750782013,
+            "min": 0.37404122948646545,
+            "max": 1.4288702011108398,
+            "count": 33
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 11401.107421875,
+            "min": 11334.9453125,
+            "max": 43346.20703125,
+            "count": 33
+        },
+        "Pyramids.Step.mean": {
+            "value": 989930.0,
+            "min": 29952.0,
+            "max": 989930.0,
+            "count": 33
+        },
+        "Pyramids.Step.sum": {
+            "value": 989930.0,
+            "min": 29952.0,
+            "max": 989930.0,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.614491879940033,
+            "min": -0.19480715692043304,
+            "max": 0.6550472378730774,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 171.4432373046875,
+            "min": -46.16929626464844,
+            "max": 187.99855041503906,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.07318393141031265,
+            "min": -0.07318393141031265,
+            "max": 0.48806479573249817,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -20.418315887451172,
+            "min": -20.418315887451172,
+            "max": 115.67135620117188,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.07170302507819586,
+            "min": 0.06538753967105197,
+            "max": 0.07364958621869604,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 1.003842351094742,
+            "min": 0.5067810199560328,
+            "max": 1.0698948174991243,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.017201309361899758,
+            "min": 0.0002177438254461774,
+            "max": 0.01736067041374987,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.2408183310665966,
+            "min": 0.002830669730800306,
+            "max": 0.24304938579249818,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.5467260558857155e-06,
+            "min": 7.5467260558857155e-06,
+            "max": 0.00029515063018788575,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00010565416478240002,
+            "min": 0.00010565416478240002,
+            "max": 0.0034887847370717994,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10251554285714286,
+            "min": 0.10251554285714286,
+            "max": 0.19838354285714285,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4352176,
+            "min": 1.3886848,
+            "max": 2.5722967999999997,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00026130273142857145,
+            "min": 0.00026130273142857145,
+            "max": 0.00983851593142857,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0036582382400000006,
+            "min": 0.0036582382400000006,
+            "max": 0.11630652718000001,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.01037752814590931,
+            "min": 0.01037752814590931,
+            "max": 0.488626629114151,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.14528539776802063,
+            "min": 0.14528539776802063,
+            "max": 3.42038631439209,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 303.81052631578945,
+            "min": 288.7864077669903,
+            "max": 999.0,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 28862.0,
+            "min": 15984.0,
+            "max": 32479.0,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6472708196379244,
+            "min": -1.0000000521540642,
+            "max": 1.6917863927275232,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 158.13799868524075,
+            "min": -31.99680168926716,
+            "max": 174.2539984509349,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6472708196379244,
+            "min": -1.0000000521540642,
+            "max": 1.6917863927275232,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 158.13799868524075,
+            "min": -31.99680168926716,
+            "max": 174.2539984509349,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.03318959897599901,
+            "min": 0.03318959897599901,
+            "max": 10.078412741422653,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.186201501695905,
+            "min": 3.186201501695905,
+            "max": 161.25460386276245,
+            "count": 33
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1685010429",
+        "python_version": "3.10.11 (main, Apr 20 2023, 19:02:41) [GCC 11.2.0]",
+        "command_line_arguments": "/home/stephen/miniconda3/envs/deep-rl-course/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --width=1280 --height=720 --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cu113",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1685011640"
+    },
+    "total": 1210.4989048200077,
+    "count": 1,
+    "self": 0.3192543479963206,
+    "children": {
+        "run_training.setup": {
+            "total": 0.013383196012000553,
+            "count": 1,
+            "self": 0.013383196012000553
+        },
+        "TrainerController.start_learning": {
+            "total": 1210.1662672759994,
+            "count": 1,
+            "self": 1.281517392519163,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 6.316212777004694,
+                    "count": 1,
+                    "self": 6.316212777004694
+                },
+                "TrainerController.advance": {
+                    "total": 1202.5078337914747,
+                    "count": 64031,
+                    "self": 1.3369778820488136,
+                    "children": {
+                        "env_step": {
+                            "total": 754.3337355441035,
+                            "count": 64031,
+                            "self": 634.0964460049872,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 119.41647095949156,
+                                    "count": 64031,
+                                    "self": 3.2679904958058614,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 116.1484804636857,
+                                            "count": 62552,
+                                            "self": 116.1484804636857
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.8208185796247562,
+                                    "count": 64031,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1208.4328184529732,
+                                            "count": 64031,
+                                            "is_parallel": true,
+                                            "self": 650.8204816541256,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0010614399943733588,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00029204398742876947,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0007693960069445893,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0007693960069445893
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.02114481398893986,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0002786679979180917,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00026757999148685485,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00026757999148685485
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.019706410996150225,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.019706410996150225
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.000892155003384687,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00018864199228119105,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.000703513011103496,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.000703513011103496
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 557.6123367988475,
+                                                    "count": 64030,
+                                                    "is_parallel": true,
+                                                    "self": 17.024892047746107,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 12.262091512457118,
+                                                            "count": 64030,
+                                                            "is_parallel": true,
+                                                            "self": 12.262091512457118
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 476.64518081813003,
+                                                            "count": 64030,
+                                                            "is_parallel": true,
+                                                            "self": 476.64518081813003
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 51.68017242051428,
+                                                            "count": 64030,
+                                                            "is_parallel": true,
+                                                            "self": 11.26647077446978,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 40.4137016460445,
+                                                                    "count": 512240,
+                                                                    "is_parallel": true,
+                                                                    "self": 40.4137016460445
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 446.83712036532233,
+                            "count": 64031,
+                            "self": 2.399169267504476,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 84.02544081573433,
+                                    "count": 64031,
+                                    "self": 83.89241295873944,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.13302785699488595,
+                                            "count": 2,
+                                            "self": 0.13302785699488595
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 360.41251028208353,
+                                    "count": 450,
+                                    "self": 212.57134403382952,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 147.841166248254,
+                                            "count": 22797,
+                                            "self": 147.841166248254
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 6.90997694619e-07,
+                    "count": 1,
+                    "self": 6.90997694619e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.06070262400317006,
+                    "count": 1,
+                    "self": 0.0008341020002262667,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.05986852200294379,
+                            "count": 1,
+                            "self": 0.05986852200294379
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499981,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499981.onnx",
+                "reward": null,
+                "creation_time": 1685011027.6336079,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-499981.pt"
+                ]
+            },
+            {
+                "steps": 999991,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999991.onnx",
+                "reward": 1.7519999891519547,
+                "creation_time": 1685011639.8715427,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-999991.pt"
+                ]
+            },
+            {
+                "steps": 1000014,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000014.onnx",
+                "reward": 1.73700001090765,
+                "creation_time": 1685011639.9351842,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1000014.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000014,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.73700001090765,
+            "creation_time": 1685011639.9351842,
+            "auxillary_file_paths": [
+                "results/Pyramids Training/Pyramids/Pyramids-1000014.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu113"
+    }
+}