Second Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08d9bd365fb5b059dfe477624c6da038029d178229222ab814d699618c68dbd5
+oid sha256:502dbd9f3894b3d80d3f609cbcae39907def0e35358b53ee15166b942d16459c
 size 1418184

Pyramids/Pyramids-1499880.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf92ee719f566070253dbe899e449351717c0926e4520f649886c06171d827ff
+size 1418184

Pyramids/Pyramids-1499880.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06188eef2b3c8043d7e115883b6823ff8d75b26c275ce9dcdb4a277da4ab1688
+size 8650990

Pyramids/Pyramids-1999877.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:502dbd9f3894b3d80d3f609cbcae39907def0e35358b53ee15166b942d16459c
+size 1418184

Pyramids/Pyramids-1999877.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29761b5e0935e6572705ecc630e4d5caf9fc1bb38b50c95c5d6494a63d0c9892
+size 8650990

Pyramids/Pyramids-2000005.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:502dbd9f3894b3d80d3f609cbcae39907def0e35358b53ee15166b942d16459c
+size 1418184

Pyramids/Pyramids-2000005.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50dae17bed14856020d1d37cf5e7eec29a6f75b7fdba5104aa6b4fa6a86d0751
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8306c63a467b35f922c15c48adfc1566cdba337d39fe8c488e5944ba1cbd12dd
+oid sha256:50dae17bed14856020d1d37cf5e7eec29a6f75b7fdba5104aa6b4fa6a86d0751
 size 8650990

Pyramids/events.out.tfevents.1693046859.3c7d3a2a16df.15444.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2d6ca5e30856149c69d937389e5e586194fc22992a56373fd10d7ad08ce2fb
+size 296494

config.json

@@ -1 +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": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "PyramidsTraining", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"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": 2000000, "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": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "PyramidsTraining", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 2000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -80,7 +80,7 @@ checkpoint_settings:
   run_id: PyramidsTraining
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55057 [Flags] 2 [Guid] 3219248762 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55165 [Flags] 2 [Guid] 4144762370 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,17 +33,10 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.086 seconds
+- Completed reload, in  0.132 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
-WARNING: Shader Did you use #pragma only_renderers and omit this platform?
-WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
-WARNING: Shader Did you use #pragma only_renderers and omit this platform?
-WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
 WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
@@ -68,7 +58,14 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.782735 ms
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 1.084830 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 4073 frames, [32.0 KB-64.0 KB]: 11636 frames, [64.0 KB-128.0 KB]: 3061 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1871 frames, [32.0 KB-64.0 KB]: 10895 frames, [64.0 KB-128.0 KB]: 6000 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
@@ -126,17 +123,17 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [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]
+    [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]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -149,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
+      Peak Allocated Bytes 480 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -186,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [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_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -207,29 +204,29 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 48 frames, [1.0 MB-2.0 MB]: 18719 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12717
+  Peak main deferred allocation count 10340
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18770 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames, [32.0 MB-64.0 MB]: 18766 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 31.1 MB
-      Peak Large allocation bytes 0 B
+      Peak Block count 2
+      Peak Allocated memory 41.4 MB
+      Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18771 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames, [4.0 MB-8.0 MB]: 18766 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.3 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 5.6 MB
+      Peak Large allocation bytes 0 B
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -255,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18770 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18766 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 18771 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18767 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,45 +270,45 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 56 frames, [1.0 MB-2.0 MB]: 18711 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 18770 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18766 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.7 MB
+      Peak Allocated memory 4.4 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 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18771 frames
+      Peak usage frame count: [0-1.0 KB]: 18767 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]: 18771 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18767 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: [16.0 KB-32.0 KB]: 18771 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18767 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 29.1 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":1693045866264,"processId":1877,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"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":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"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}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1693049565439,"processId":15464,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"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":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"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

@@ -2,171 +2,171 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.2925526201725006,
-            "min": 0.2925526201725006,
-            "max": 1.4079902172088623,
+            "value": 0.189856618642807,
+            "min": 0.1817089468240738,
+            "max": 0.3481859266757965,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 8753.1748046875,
-            "min": 8753.1748046875,
-            "max": 42712.79296875,
+            "value": 5726.07568359375,
+            "min": 5480.341796875,
+            "max": 10272.8779296875,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 249.94573643410854,
+            "min": 230.5703125,
+            "max": 364.6666666666667,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 32243.0,
+            "min": 17353.0,
+            "max": 32243.0,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989995.0,
-            "min": 29875.0,
-            "max": 989995.0,
+            "value": 1979995.0,
+            "min": 1019988.0,
+            "max": 1979995.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989995.0,
-            "min": 29875.0,
-            "max": 989995.0,
+            "value": 1979995.0,
+            "min": 1019988.0,
+            "max": 1979995.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.5299193859100342,
-            "min": -0.09536299854516983,
-            "max": 0.5479076504707336,
+            "value": 0.7693508267402649,
+            "min": 0.5625669956207275,
+            "max": 0.8056074380874634,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 148.9073486328125,
-            "min": -22.98248291015625,
-            "max": 150.6746063232422,
+            "value": 230.8052520751953,
+            "min": 103.35254669189453,
+            "max": 238.45980834960938,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.019237598404288292,
-            "min": -0.006457205396145582,
-            "max": 0.366727739572525,
+            "value": -0.004943689797073603,
+            "min": -0.004943689797073603,
+            "max": 0.04152600094676018,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 5.405765056610107,
-            "min": -1.7563598155975342,
-            "max": 86.91447448730469,
-            "count": 33
-        },
-        "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06525196186183686,
-            "min": 0.06525196186183686,
-            "max": 0.07628083501195314,
-            "count": 33
-        },
-        "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.913527466065716,
-            "min": 0.533965845083672,
-            "max": 1.0677466315291122,
+            "value": -1.4831069707870483,
+            "min": -1.4831069707870483,
+            "max": 11.83491039276123,
             "count": 33
         },
-        "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0153241059514195,
-            "min": 0.0012688146210703885,
-            "max": 0.0166074233037703,
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.735264048911631,
+            "min": 1.5612444244785073,
+            "max": 1.7675039833784103,
             "count": 33
         },
-        "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.214537483319873,
-            "min": 0.012688146210703886,
-            "max": 0.23250392625278418,
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 222.11379826068878,
+            "min": 96.64699840545654,
+            "max": 228.18799858540297,
             "count": 33
         },
-        "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.509247496949995e-06,
-            "min": 7.509247496949995e-06,
-            "max": 0.00029523621587364284,
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.735264048911631,
+            "min": 1.5612444244785073,
+            "max": 1.7675039833784103,
             "count": 33
         },
-        "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010512946495729993,
-            "min": 0.00010512946495729993,
-            "max": 0.003509696930101099,
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 222.11379826068878,
+            "min": 96.64699840545654,
+            "max": 228.18799858540297,
             "count": 33
         },
-        "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10250305000000001,
-            "min": 0.10250305000000001,
-            "max": 0.19841207142857145,
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.02587083513401467,
+            "min": 0.024559607545597828,
+            "max": 0.05238411585616385,
             "count": 33
         },
-        "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4350427000000001,
-            "min": 1.3888845,
-            "max": 2.5698989,
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.3114668971538777,
+            "min": 2.692943104368169,
+            "max": 4.350430508609861,
             "count": 33
         },
-        "Pyramids.Policy.Beta.mean": {
-            "value": 0.00026005469499999995,
-            "min": 0.00026005469499999995,
-            "max": 0.009841365935714285,
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06605385297734756,
+            "min": 0.06359199066323021,
+            "max": 0.07284611712836957,
             "count": 33
         },
-        "Pyramids.Policy.Beta.sum": {
-            "value": 0.003640765729999999,
-            "min": 0.003640765729999999,
-            "max": 0.11701290011000001,
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9247539416828658,
+            "min": 0.5931617736607543,
+            "max": 1.040361449122429,
             "count": 33
         },
-        "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.016181940212845802,
-            "min": 0.01593572273850441,
-            "max": 0.4101909101009369,
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.01609122662089898,
+            "min": 0.01255998326559973,
+            "max": 0.016918032216317415,
             "count": 33
         },
-        "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.22654716670513153,
-            "min": 0.22310012578964233,
-            "max": 2.8713364601135254,
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.22527717269258574,
+            "min": 0.11886353706301866,
+            "max": 0.23685245102844382,
             "count": 33
         },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 341.77894736842103,
-            "min": 332.39285714285717,
-            "max": 999.0,
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 5.261755388971429e-06,
+            "min": 5.261755388971429e-06,
+            "max": 0.00014841648386118886,
             "count": 33
         },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 32469.0,
-            "min": 16674.0,
-            "max": 32469.0,
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 7.36645754456e-05,
+            "min": 7.36645754456e-05,
+            "max": 0.0020265499244836002,
             "count": 33
         },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.5739747156438075,
-            "min": -0.9999750521965325,
-            "max": 1.6199737903440283,
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10175388571428572,
+            "min": 0.10175388571428572,
+            "max": 0.14947214444444443,
             "count": 33
         },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 149.5275979861617,
-            "min": -31.99920167028904,
-            "max": 149.5275979861617,
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4245544,
+            "min": 1.3452492999999999,
+            "max": 2.1336950999999997,
             "count": 33
         },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.5739747156438075,
-            "min": -0.9999750521965325,
-            "max": 1.6199737903440283,
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00018521318285714286,
+            "min": 0.00018521318285714286,
+            "max": 0.00495226723,
             "count": 33
         },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 149.5275979861617,
-            "min": -31.99920167028904,
-            "max": 149.5275979861617,
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.00259298456,
+            "min": 0.00259298456,
+            "max": 0.06762408835999999,
             "count": 33
         },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.056505663878526416,
-            "min": 0.056505663878526416,
-            "max": 7.6237235901986855,
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.009953402914106846,
+            "min": 0.009953402914106846,
+            "max": 0.015164068900048733,
             "count": 33
         },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 5.3680380684600095,
-            "min": 4.82987459161086,
-            "max": 129.60330103337765,
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.139347642660141,
+            "min": 0.13647662103176117,
+            "max": 0.2004043012857437,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,67 +184,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1693043632",
+        "start_time_seconds": "1693046857",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1693045866"
+        "end_time_seconds": "1693049565"
     },
-    "total": 2233.740041313,
+    "total": 2707.949965885,
     "count": 1,
-    "self": 0.6864014779998797,
+    "self": 0.4775602929998968,
     "children": {
         "run_training.setup": {
-            "total": 0.042223416000013,
+            "total": 0.0623524739999084,
             "count": 1,
-            "self": 0.042223416000013
+            "self": 0.0623524739999084
         },
         "TrainerController.start_learning": {
-            "total": 2233.011416419,
+            "total": 2707.410053118,
             "count": 1,
-            "self": 1.372872119040494,
+            "self": 1.6329233869714699,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.35133397300001,
+                    "total": 5.2107627870000215,
                     "count": 1,
-                    "self": 5.35133397300001
+                    "self": 5.2107627870000215
                 },
                 "TrainerController.advance": {
-                    "total": 2226.1392910869595,
-                    "count": 63894,
-                    "self": 1.3391438549979284,
+                    "total": 2700.4612155600284,
+                    "count": 65365,
+                    "self": 1.561065242126915,
                     "children": {
                         "env_step": {
-                            "total": 1550.4180203630044,
-                            "count": 63894,
-                            "self": 1441.4861008679884,
+                            "total": 2008.4881389168577,
+                            "count": 65365,
+                            "self": 1891.3168267420342,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 108.10190907500134,
-                                    "count": 63894,
-                                    "self": 4.717187727024566,
+                                    "total": 116.24314791791585,
+                                    "count": 65365,
+                                    "self": 4.9299677619242175,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 103.38472134797678,
-                                            "count": 62568,
-                                            "self": 103.38472134797678
+                                            "total": 111.31318015599163,
+                                            "count": 62555,
+                                            "self": 111.31318015599163
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.8300104200147302,
-                                    "count": 63894,
+                                    "total": 0.9281642569076212,
+                                    "count": 65365,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2227.7562670940065,
-                                            "count": 63894,
+                                            "total": 2700.989232571038,
+                                            "count": 65365,
                                             "is_parallel": true,
-                                            "self": 901.1996086510462,
+                                            "self": 936.2675088729279,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.006092556999988119,
+                                                            "total": 0.002749479999692994,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.004329571000027954,
+                                                            "self": 0.0006598020004275895,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001762985999960165,
+                                                                    "total": 0.0020896779992654047,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001762985999960165
+                                                                    "self": 0.0020896779992654047
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.0851080310000043,
+                                                            "total": 0.05014101799997661,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005822329999318754,
+                                                            "self": 0.0005669600000146602,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004699710000295454,
+                                                                    "total": 0.0005053139998381084,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004699710000295454
+                                                                    "self": 0.0005053139998381084
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.08213021400001708,
+                                                                    "total": 0.04710479200002737,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.08213021400001708
+                                                                    "self": 0.04710479200002737
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0019256130000258054,
+                                                                    "total": 0.0019639520000964694,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004461659999606127,
+                                                                    "self": 0.000376612000309251,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014794470000651927,
+                                                                            "total": 0.0015873399997872184,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014794470000651927
+                                                                            "self": 0.0015873399997872184
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1326.5566584429603,
-                                                    "count": 63893,
+                                                    "total": 1764.72172369811,
+                                                    "count": 65364,
                                                     "is_parallel": true,
-                                                    "self": 34.24054019500113,
+                                                    "self": 35.592770060198745,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 23.18486159997883,
-                                                            "count": 63893,
+                                                            "total": 23.265593657970385,
+                                                            "count": 65364,
                                                             "is_parallel": true,
-                                                            "self": 23.18486159997883
+                                                            "self": 23.265593657970385
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1164.683439188993,
-                                                            "count": 63893,
+                                                            "total": 1593.6019322240054,
+                                                            "count": 65364,
                                                             "is_parallel": true,
-                                                            "self": 1164.683439188993
+                                                            "self": 1593.6019322240054
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 104.44781745898746,
-                                                            "count": 63893,
+                                                            "total": 112.26142775593553,
+                                                            "count": 65364,
                                                             "is_parallel": true,
-                                                            "self": 20.28788323680874,
+                                                            "self": 22.869903264721415,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 84.15993422217872,
-                                                                    "count": 511144,
+                                                                    "total": 89.39152449121411,
+                                                                    "count": 522912,
                                                                     "is_parallel": true,
-                                                                    "self": 84.15993422217872
+                                                                    "self": 89.39152449121411
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 674.3821268689571,
-                            "count": 63894,
-                            "self": 2.693971217939634,
+                            "total": 690.4120114010439,
+                            "count": 65365,
+                            "self": 3.0458836080670153,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 113.54063969001822,
-                                    "count": 63894,
-                                    "self": 113.27685059101827,
+                                    "total": 120.1345750539781,
+                                    "count": 65365,
+                                    "self": 119.91976739297888,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.2637890989999505,
+                                            "total": 0.2148076609992131,
                                             "count": 2,
-                                            "self": 0.2637890989999505
+                                            "self": 0.2148076609992131
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 558.1475159609993,
-                                    "count": 454,
-                                    "self": 367.21057592700845,
+                                    "total": 567.2315527389987,
+                                    "count": 471,
+                                    "self": 371.40067953005564,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 190.93694003399082,
-                                            "count": 22794,
-                                            "self": 190.93694003399082
+                                            "total": 195.8308732089431,
+                                            "count": 22692,
+                                            "self": 195.8308732089431
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.5609998627041932e-06,
+                    "total": 9.820005288929678e-07,
                     "count": 1,
-                    "self": 1.5609998627041932e-06
+                    "self": 9.820005288929678e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.14791767899987462,
+                    "total": 0.10515040199970827,
                     "count": 1,
-                    "self": 0.0019460690000414615,
+                    "self": 0.0016279530000247178,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.14597160999983316,
+                            "total": 0.10352244899968355,
                             "count": 1,
-                            "self": 0.14597160999983316
+                            "self": 0.10352244899968355
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,15 +1,6 @@
 {
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 499992,
-                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-499992.onnx",
-                "reward": null,
-                "creation_time": 1693044674.0251918,
-                "auxillary_file_paths": [
-                    "results/PyramidsTraining/Pyramids/Pyramids-499992.pt"
-                ]
-            },
             {
                 "steps": 999890,
                 "file_path": "results/PyramidsTraining/Pyramids/Pyramids-999890.onnx",
@@ -27,15 +18,42 @@
                 "auxillary_file_paths": [
                     "results/PyramidsTraining/Pyramids/Pyramids-1000018.pt"
                 ]
+            },
+            {
+                "steps": 1499880,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1499880.onnx",
+                "reward": 1.8224285628114427,
+                "creation_time": 1693048213.750938,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-1499880.pt"
+                ]
+            },
+            {
+                "steps": 1999877,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1999877.onnx",
+                "reward": 1.7714999821037054,
+                "creation_time": 1693049564.9060664,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-1999877.pt"
+                ]
+            },
+            {
+                "steps": 2000005,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-2000005.onnx",
+                "reward": 1.7714999821037054,
+                "creation_time": 1693049565.0193465,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-2000005.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000018,
+            "steps": 2000005,
             "file_path": "results/PyramidsTraining/Pyramids.onnx",
-            "reward": 1.6974999867379665,
-            "creation_time": 1693045865.6458752,
+            "reward": 1.7714999821037054,
+            "creation_time": 1693049565.0193465,
             "auxillary_file_paths": [
-                "results/PyramidsTraining/Pyramids/Pyramids-1000018.pt"
+                "results/PyramidsTraining/Pyramids/Pyramids-2000005.pt"
             ]
         }
     },