Adjusted parameters

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9bb3a8af92f4b133d0472f540d1acfb2b47091353cea77aa845388a6350fc40
+oid sha256:2202ce134f5c363d9184eea66cede604f3ce94f889c109cf5fd6682776346c4d
 size 1417437

Pyramids/{Pyramids-1000064.onnx → Pyramids-1499928.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9bb3a8af92f4b133d0472f540d1acfb2b47091353cea77aa845388a6350fc40
+oid sha256:41737e9c5bca314c9e1dd391758a68b6272ac4c2a015b4c0cb836856ba20b352
 size 1417437

Pyramids/{Pyramids-499927.pt → Pyramids-1499928.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d8552a5e7a8b68da10eb66394601983424046f43ea81671151cf5996464ee0
+oid sha256:5289d0513b8a9e09e238629b330663cca608e437729bad46f2e9d1f0dd422afb
 size 8652382

Pyramids/{Pyramids-999985.onnx → Pyramids-1999927.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9bb3a8af92f4b133d0472f540d1acfb2b47091353cea77aa845388a6350fc40
+oid sha256:f811e4f96b315f4bd89a9bc3dd8204d85acae0e5535cb75f2969d5f22f28e6c6
 size 1417437

Pyramids/{Pyramids-1000064.pt → Pyramids-1999927.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1510b7f4f6d2ae1d80d5cc71f566164e0f9217d455fd309b4a55a184b7829cc3
+oid sha256:0d8bfee5b34d846f32b77ab23eb9a0c9791abf13e74105fc62ea6a258331cb63
 size 8652382

Pyramids/{Pyramids-499927.onnx → Pyramids-2499964.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2a4c6e40d2db09df89c511ea1922b92a458b94f05f907b422a010373d0fcf54
+oid sha256:4307a8ab5b640d5a30e0da5feb352ff6c526ddd93e4b52e4c0748aea95da8f25
 size 1417437

Pyramids/{Pyramids-999985.pt → Pyramids-2499964.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:729fc69d87a27f81df37a7bc0fae032575223de65fe2439243fad4c7134b6c08
+oid sha256:4823423adabc6c3afc97771af33e36a38066633c73befaab9d8ce977a96ede9f
 size 8652382

Pyramids/{Pyramids-24192.pt → Pyramids-2999981.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9565db4d50e0dbef463f52b139b5a5974a8da3ef61c0c825f71958641df9c393
-size 241
+oid sha256:2202ce134f5c363d9184eea66cede604f3ce94f889c109cf5fd6682776346c4d
+size 1417437

Pyramids/Pyramids-2999981.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b817aa1a046a3b3774bd1ebc56f7eaa15725cf78b89f623a8b62654fb3dd33
+size 8652382

Pyramids/Pyramids-3000109.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2202ce134f5c363d9184eea66cede604f3ce94f889c109cf5fd6682776346c4d
+size 1417437

Pyramids/Pyramids-3000109.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065a50526f49c5eb5973cf6b260552c8948f11ce55199be31377c58b6155621c
+size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1510b7f4f6d2ae1d80d5cc71f566164e0f9217d455fd309b4a55a184b7829cc3
+oid sha256:065a50526f49c5eb5973cf6b260552c8948f11ce55199be31377c58b6155621c
 size 8652382

Pyramids/{events.out.tfevents.1673709222.cc33aa7b43a4.2690.0 → events.out.tfevents.1673783629.1621ca8d36da.20573.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91ae147a256e4ebfa4bb99cf7e0caa4c1595f56d41528d306386ddeacdd43bce
-size 323677
+oid sha256:b7c3b91917158977ea5ee166bc813f677f3cf241556c89f185133a78119bc9a9
+size 998771

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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "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": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "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": 256, "buffer_size": 2048, "learning_rate": 0.0001, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 3000000, "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": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -3,13 +3,13 @@ behaviors:
   Pyramids:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 128
+      batch_size: 256
       buffer_size: 2048
-      learning_rate: 0.0003
+      learning_rate: 0.0001
       beta: 0.01
       epsilon: 0.2
       lambd: 0.95
-      num_epoch: 3
+      num_epoch: 5
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
@@ -49,7 +49,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     checkpoint_interval: 500000
-    max_steps: 1000000
+    max_steps: 3000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,9 +1,12 @@
 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) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55055 [Flags] 2 [Guid] 364859310 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.2 [Port] 55083 [Flags] 2 [Guid] 218355938 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [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
@@ -33,7 +36,7 @@ ALSA lib pcm.c:2495:(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  0.081 seconds
+- Completed reload, in  0.091 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)
@@ -65,7 +68,7 @@ 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: 0.967208 ms
+UnloadTime: 0.794913 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.
@@ -73,7 +76,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 2910 frames, [32.0 KB-64.0 KB]: 13103 frames, [64.0 KB-128.0 KB]: 2755 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3888 frames, [32.0 KB-64.0 KB]: 40923 frames, [64.0 KB-128.0 KB]: 11453 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
@@ -204,28 +207,28 @@ 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]: 18470 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55966 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 12624
+  Peak main deferred allocation count 12047
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.6 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18767 frames, [32.0 MB-64.0 MB]: 1 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 56264 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 32.2 MB
+      Peak Allocated memory 31.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18769 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56265 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 21.3 MB
+      Peak Allocated memory 22.0 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -254,13 +257,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.6 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18768 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 56264 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]: 18769 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 56265 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,13 +275,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.6 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55966 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]: 18768 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 56264 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
@@ -290,19 +293,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.6 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18769 frames
+      Peak usage frame count: [0-1.0 KB]: 56265 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]: 18769 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 56265 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]: 18769 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 56265 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -311,4 +314,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673711273004,"processId":2709,"allocatedMemory":1957332,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"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":1673791034412,"processId":20594,"allocatedMemory":1957332,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"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

@@ -2,189 +2,189 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.3963216245174408,
-            "min": 0.37892216444015503,
-            "max": 1.4495625495910645,
-            "count": 33
+            "value": 0.172193706035614,
+            "min": 0.1647656112909317,
+            "max": 1.4083733558654785,
+            "count": 100
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 12060.859375,
-            "min": 11373.6796875,
-            "max": 43973.9296875,
-            "count": 33
+            "value": 5141.01513671875,
+            "min": 4979.8759765625,
+            "max": 42724.4140625,
+            "count": 100
         },
         "Pyramids.Step.mean": {
-            "value": 989936.0,
+            "value": 2999981.0,
             "min": 29952.0,
-            "max": 989936.0,
-            "count": 33
+            "max": 2999981.0,
+            "count": 100
         },
         "Pyramids.Step.sum": {
-            "value": 989936.0,
+            "value": 2999981.0,
             "min": 29952.0,
-            "max": 989936.0,
-            "count": 33
+            "max": 2999981.0,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.43158861994743347,
-            "min": -0.0929163247346878,
-            "max": 0.5519277453422546,
-            "count": 33
+            "value": 0.6161277294158936,
+            "min": -0.09271835535764694,
+            "max": 0.6173363924026489,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 117.39210510253906,
-            "min": -22.392833709716797,
-            "max": 154.53976440429688,
-            "count": 33
+            "value": 174.36415100097656,
+            "min": -22.530559539794922,
+            "max": 174.36415100097656,
+            "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.0027870223857462406,
-            "min": -0.00042706672684289515,
-            "max": 0.23599685728549957,
-            "count": 33
+            "value": -0.014366395771503448,
+            "min": -1.7395180463790894,
+            "max": 1.7319082021713257,
+            "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 0.7580701112747192,
-            "min": -0.11402681469917297,
-            "max": 55.93125534057617,
-            "count": 33
+            "value": -4.065690040588379,
+            "min": -455.75372314453125,
+            "max": 453.75994873046875,
+            "count": 100
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06696148093582856,
-            "min": 0.062427873386958585,
-            "max": 0.07537894976558164,
-            "count": 33
+            "value": 0.04603456548027074,
+            "min": 0.04314542232702175,
+            "max": 0.0513265693273956,
+            "count": 100
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 1.0044222140374284,
-            "min": 0.49671674601435284,
-            "max": 1.1306842464837246,
-            "count": 33
+            "value": 0.6905184822040611,
+            "min": 0.33428702012669026,
+            "max": 0.7394997566007078,
+            "count": 100
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01608618958335784,
-            "min": 0.000992208526063701,
-            "max": 0.01623464779271439,
-            "count": 33
+            "value": 0.015738900086532035,
+            "min": 0.00041164355064317423,
+            "max": 0.40088433486276437,
+            "count": 100
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.24129284375036758,
-            "min": 0.0075454792245495655,
-            "max": 0.24129284375036758,
-            "count": 33
+            "value": 0.23608350129798053,
+            "min": 0.004528079057074917,
+            "max": 5.6123806880787015,
+            "count": 100
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.573997475366666e-06,
-            "min": 7.573997475366666e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 4.911817311399989e-07,
+            "min": 4.911817311399989e-07,
+            "max": 9.946118149120001e-05,
+            "count": 100
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00011360996213049999,
-            "min": 0.00011360996213049999,
-            "max": 0.0035081249306250996,
-            "count": 33
+            "value": 7.367725967099983e-06,
+            "min": 7.367725967099983e-06,
+            "max": 0.0013274454725547,
+            "count": 100
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10252463333333336,
-            "min": 0.10252463333333336,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10049108222222224,
+            "min": 0.10049108222222224,
+            "max": 0.19946118095238097,
+            "count": 100
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.5378695000000004,
-            "min": 1.3691136000000002,
-            "max": 2.5693748999999997,
-            "count": 33
+            "value": 1.5073662333333335,
+            "min": 1.3897045333333333,
+            "max": 2.8274453000000004,
+            "count": 100
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00026221087,
-            "min": 0.00026221087,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 5.905911399999989e-05,
+            "min": 5.905911399999989e-05,
+            "max": 0.009946171977142856,
+            "count": 100
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.003933163050000001,
-            "min": 0.003933163050000001,
-            "max": 0.11696055251,
-            "count": 33
+            "value": 0.0008858867099999984,
+            "min": 0.0008858867099999984,
+            "max": 0.13276178547,
+            "count": 100
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.00945773720741272,
-            "min": 0.009271085262298584,
-            "max": 0.3552553951740265,
-            "count": 33
+            "value": 0.026145173236727715,
+            "min": 0.026145173236727715,
+            "max": 0.5980517268180847,
+            "count": 100
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.1418660581111908,
-            "min": 0.12979519367218018,
-            "max": 2.486787796020508,
-            "count": 33
+            "value": 0.39217761158943176,
+            "min": 0.36809539794921875,
+            "max": 4.186362266540527,
+            "count": 100
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 435.5844155844156,
-            "min": 361.8152173913044,
+            "value": 310.4,
+            "min": 289.4848484848485,
             "max": 999.0,
-            "count": 33
+            "count": 100
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 33540.0,
+            "value": 29488.0,
             "min": 15984.0,
-            "max": 33540.0,
-            "count": 33
+            "max": 34277.0,
+            "count": 100
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.3825324446736993,
+            "value": 1.6895999808060496,
             "min": -1.0000000521540642,
-            "max": 1.5077173760079818,
-            "count": 33
+            "max": 1.6911179810762405,
+            "count": 100
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 106.45499823987484,
+            "value": 160.5119981765747,
             "min": -32.000001668930054,
-            "max": 138.70999859273434,
-            "count": 33
+            "max": 169.11179810762405,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.3825324446736993,
+            "value": 1.6895999808060496,
             "min": -1.0000000521540642,
-            "max": 1.5077173760079818,
-            "count": 33
+            "max": 1.6911179810762405,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 106.45499823987484,
+            "value": 160.5119981765747,
             "min": -32.000001668930054,
-            "max": 138.70999859273434,
-            "count": 33
+            "max": 169.11179810762405,
+            "count": 100
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.04263687019112411,
-            "min": 0.03542026030481793,
-            "max": 6.730314579792321,
-            "count": 33
+            "value": 0.08286011184835317,
+            "min": 0.07857821287703701,
+            "max": 11.01363092660904,
+            "count": 100
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 3.2830390047165565,
-            "min": 2.6668454946629936,
-            "max": 107.68503327667713,
-            "count": 33
+            "value": 7.8717106255935505,
+            "min": 7.174652462999802,
+            "max": 176.21809482574463,
+            "count": 100
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 100
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 100
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673709219",
+        "start_time_seconds": "1673783626",
         "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
         "mlagents_version": "0.29.0.dev0",
@@ -192,66 +192,66 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1673711273"
+        "end_time_seconds": "1673791034"
     },
-    "total": 2053.37231426,
+    "total": 7408.060608971001,
     "count": 1,
-    "self": 0.487154233000183,
+    "self": 0.4775461550007094,
     "children": {
         "run_training.setup": {
-            "total": 0.11296040399997764,
+            "total": 0.11163453599965578,
             "count": 1,
-            "self": 0.11296040399997764
+            "self": 0.11163453599965578
         },
         "TrainerController.start_learning": {
-            "total": 2052.7721996230002,
+            "total": 7407.4714282800005,
             "count": 1,
-            "self": 1.2402444569856925,
+            "self": 5.1130147120175025,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.496398377999981,
+                    "total": 6.665063098000246,
                     "count": 1,
-                    "self": 6.496398377999981
+                    "self": 6.665063098000246
                 },
                 "TrainerController.advance": {
-                    "total": 2044.9392552420145,
-                    "count": 63764,
-                    "self": 1.307802944031664,
+                    "total": 7395.578573279985,
+                    "count": 192507,
+                    "self": 5.180274127194934,
                     "children": {
                         "env_step": {
-                            "total": 1380.8280767199785,
-                            "count": 63764,
-                            "self": 1274.9483338659165,
+                            "total": 4772.939104372194,
+                            "count": 192507,
+                            "self": 4390.172587254402,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 105.10758953706988,
-                                    "count": 63764,
-                                    "self": 4.38078287908786,
+                                    "total": 379.5830282929637,
+                                    "count": 192507,
+                                    "self": 15.347926996098977,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 100.72680665798202,
-                                            "count": 62561,
-                                            "self": 34.03783737599417,
+                                            "total": 364.23510129686474,
+                                            "count": 187549,
+                                            "self": 121.69350056174335,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 66.68896928198785,
-                                                    "count": 62561,
-                                                    "self": 66.68896928198785
+                                                    "total": 242.5416007351214,
+                                                    "count": 187549,
+                                                    "self": 242.5416007351214
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7721533169919894,
-                                    "count": 63764,
+                                    "total": 3.1834888248286006,
+                                    "count": 192507,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2048.2412592330234,
-                                            "count": 63764,
+                                            "total": 7391.3437224265335,
+                                            "count": 192507,
                                             "is_parallel": true,
-                                            "self": 872.4286040499896,
+                                            "self": 3360.819595076673,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.001805626999953347,
+                                                            "total": 0.0019106769996142248,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000685975999999755,
+                                                            "self": 0.0006517159990835353,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001119650999953592,
+                                                                    "total": 0.0012589610005306895,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001119650999953592
+                                                                    "self": 0.0012589610005306895
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05277994700009003,
+                                                            "total": 0.04981924700041418,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005411750000803295,
+                                                            "self": 0.0005316970000421861,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005054120000522744,
+                                                                    "total": 0.0004576800001814263,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005054120000522744
+                                                                    "self": 0.0004576800001814263
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.05002884099997118,
+                                                                    "total": 0.04700930600029096,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.05002884099997118
+                                                                    "self": 0.04700930600029096
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017045189999862487,
+                                                                    "total": 0.0018205639998996048,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00046017399972697604,
+                                                                    "self": 0.0004515860009632888,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0012443450002592726,
+                                                                            "total": 0.001368977998936316,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0012443450002592726
+                                                                            "self": 0.001368977998936316
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1175.8126551830337,
-                                                    "count": 63763,
+                                                    "total": 4030.5241273498605,
+                                                    "count": 192506,
                                                     "is_parallel": true,
-                                                    "self": 28.385981297061335,
+                                                    "self": 93.57510296254623,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 24.030136245979634,
-                                                            "count": 63763,
+                                                            "total": 77.95089503732379,
+                                                            "count": 192506,
                                                             "is_parallel": true,
-                                                            "self": 24.030136245979634
+                                                            "self": 77.95089503732379
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1017.9619269290041,
-                                                            "count": 63763,
+                                                            "total": 3511.6009194647468,
+                                                            "count": 192506,
                                                             "is_parallel": true,
-                                                            "self": 1017.9619269290041
+                                                            "self": 3511.6009194647468
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 105.43461071098875,
-                                                            "count": 63763,
+                                                            "total": 347.3972098852437,
+                                                            "count": 192506,
                                                             "is_parallel": true,
-                                                            "self": 23.384566760032158,
+                                                            "self": 78.90584047933771,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 82.05004395095659,
-                                                                    "count": 510104,
+                                                                    "total": 268.49136940590597,
+                                                                    "count": 1540048,
                                                                     "is_parallel": true,
-                                                                    "self": 82.05004395095659
+                                                                    "self": 268.49136940590597
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 662.8033755780043,
-                            "count": 63764,
-                            "self": 2.202008867012296,
+                            "total": 2617.4591947805957,
+                            "count": 192507,
+                            "self": 9.635674524552996,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 150.2878955409965,
-                                    "count": 63764,
-                                    "self": 150.0755036999965,
+                                    "total": 479.09892203501477,
+                                    "count": 192507,
+                                    "self": 478.4984932260122,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.21239184099999875,
-                                            "count": 2,
-                                            "self": 0.21239184099999875
+                                            "total": 0.6004288090025511,
+                                            "count": 6,
+                                            "self": 0.6004288090025511
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 510.3134711699955,
-                                    "count": 446,
-                                    "self": 193.58307704400738,
+                                    "total": 2128.724598221028,
+                                    "count": 1391,
+                                    "self": 996.1768557010346,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 316.73039412598814,
-                                            "count": 22773,
-                                            "self": 316.73039412598814
+                                            "total": 1132.5477425199933,
+                                            "count": 56690,
+                                            "self": 1132.5477425199933
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0690000635804608e-06,
+                    "total": 9.919986041495577e-07,
                     "count": 1,
-                    "self": 1.0690000635804608e-06
+                    "self": 9.919986041495577e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09630047700011346,
+                    "total": 0.11477619799916283,
                     "count": 1,
-                    "self": 0.0014672840002276644,
+                    "self": 0.0014028049990884028,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.0948331929998858,
+                            "total": 0.11337339300007443,
                             "count": 1,
-                            "self": 0.0948331929998858
+                            "self": 0.11337339300007443
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499927,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499927.onnx",
-                "reward": 1.6300000324845314,
-                "creation_time": 1673710188.7621791,
+                "steps": 1499928,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499928.onnx",
+                "reward": 1.7164999544620514,
+                "creation_time": 1673787174.8848825,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499927.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1499928.pt"
                 ]
             },
             {
-                "steps": 999985,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999985.onnx",
-                "reward": 1.156199972331524,
-                "creation_time": 1673711272.438426,
+                "steps": 1999927,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999927.onnx",
+                "reward": 1.7209999859333038,
+                "creation_time": 1673788444.4714148,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999985.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1999927.pt"
                 ]
             },
             {
-                "steps": 1000064,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000064.onnx",
-                "reward": 1.1558332927525043,
-                "creation_time": 1673711272.5450068,
+                "steps": 2499964,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499964.onnx",
+                "reward": 1.5172500237822533,
+                "creation_time": 1673789713.851386,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000064.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2499964.pt"
+                ]
+            },
+            {
+                "steps": 2999981,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999981.onnx",
+                "reward": null,
+                "creation_time": 1673791033.8515344,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2999981.pt"
+                ]
+            },
+            {
+                "steps": 3000109,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000109.onnx",
+                "reward": null,
+                "creation_time": 1673791033.9810536,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-3000109.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000064,
+            "steps": 3000109,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.1558332927525043,
-            "creation_time": 1673711272.5450068,
+            "reward": null,
+            "creation_time": 1673791033.9810536,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000064.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-3000109.pt"
             ]
         }
     },