First Pyramids

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0f70840f0ca948d2debd6a6f3e7383918a8342004cf594c15df1faf9cf7a9f8
+oid sha256:ba1d8d2e775e1ca96d118e3272eb69ea4d974db2521d2491bae54a8d4af3f355
 size 1417437

Pyramids/{Pyramids-199947.onnx → Pyramids-1000002.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e975e3cc0af91d9643060377c1ba81c84a62cab81cc7a9539d5cb1c6aa9bd729
+oid sha256:ba1d8d2e775e1ca96d118e3272eb69ea4d974db2521d2491bae54a8d4af3f355
 size 1417437

Pyramids/{Pyramids-399927.pt → Pyramids-1000002.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb062c7cdeacc54953eabc3f0744ded5259e66bdf189e47a46cfb2a45c12c44
+oid sha256:cf25bdc4ead0cff3999c654787246ff21f9ff84645c856f4c31539dd1fc65095
 size 8651427

Pyramids/Pyramids-500089.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d0f70840f0ca948d2debd6a6f3e7383918a8342004cf594c15df1faf9cf7a9f8
-size 1417437

Pyramids/Pyramids-500089.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:39875887eee9570481378ee5a7ef31fc448c58bb6a16cc97c76351161041d171
-size 8651427

Pyramids/{Pyramids-399927.onnx → Pyramids-699878.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4397e92e8f3d828e8fc68a897a0cdf69dfe0397db8fccc2f63b37a571da743c3
+oid sha256:7485fcf38620963c7456b538c9c32a0abac745c15306502b0bdaecaedb342ad1
 size 1417437

Pyramids/{Pyramids-199947.pt → Pyramids-699878.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deb30cadb0458756e6fc97f5bc5adb64b0f6078119ac62df6897286c5bf46efe
+oid sha256:2098b5ef602926bcca0701369778c505f8a1777c97534e0925445866abf7c46e
 size 8651427

Pyramids/{Pyramids-299952.onnx → Pyramids-799911.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e2c59cf524a624e6569b66c6150240c3bb1212335e456274577a80871dc98c
+oid sha256:1b92b83875fbfa35f691143300df76b5370f9580160c4da6cd30245147337839
 size 1417437

Pyramids/{Pyramids-499961.pt → Pyramids-799911.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2556c1cdd9816cacd0a0d5fac8883ae586b66095fcd6a9ca0465189de3f48531
+oid sha256:971c2aeaf4f6c3fbc5ed934da3071f7700ea4a4b931e382abe508b7435a5c07c
 size 8651427

Pyramids/{Pyramids-499961.onnx → Pyramids-899924.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0f70840f0ca948d2debd6a6f3e7383918a8342004cf594c15df1faf9cf7a9f8
+oid sha256:a3bf7beeb43695b774d46d62aeebe5d215532351c8de2800f622082c68231a29
 size 1417437

Pyramids/{Pyramids-299952.pt → Pyramids-899924.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b631f7f30dd028556dd9e15b3fa4535578e27acbc05a28d1a4121e95c3b056cb
+oid sha256:3abf0d8f3cfcabcbbeaf31c1d08efb2657c2819abe0031a4e554296183e0ceaf
 size 8651427

Pyramids/Pyramids-999874.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1d8d2e775e1ca96d118e3272eb69ea4d974db2521d2491bae54a8d4af3f355
+size 1417437

Pyramids/Pyramids-999874.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d385e6e543a0720fd31813eb4478388591cb1f5f2a80ecc76de4c5c527fabb13
+size 8651427

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39875887eee9570481378ee5a7ef31fc448c58bb6a16cc97c76351161041d171
+oid sha256:cf25bdc4ead0cff3999c654787246ff21f9ff84645c856f4c31539dd1fc65095
 size 8651427

Pyramids/{events.out.tfevents.1657726190.2775460de6ad.260.0 → events.out.tfevents.1657728195.2775460de6ad.914.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87d46fa28aeb0dd5e437382111c9b5d877097449598354854546f92a0dce8c57
-size 104615
+oid sha256:af6cd4e8a3a971a5a88f3c9f785c581c867960210095d8792d44632b09c35097
+size 198861

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": 100000, "max_steps": 500000, "time_horizon": 128, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-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": 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, "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": 100000, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-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_Training1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -49,7 +49,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     checkpoint_interval: 100000
-    max_steps: 500000
+    max_steps: 1000000
     time_horizon: 128
     summary_freq: 50000
     threaded: false
@@ -75,7 +75,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids_Training
+  run_id: Pyramids_Training1
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/trained-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] 55258 [Flags] 2 [Guid] 2335508585 [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] 55016 [Flags] 2 [Guid] 3136713205 [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/trained-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ 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  0.133 seconds
+- Completed reload, in  0.154 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)
@@ -68,7 +65,7 @@ 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: 1.307987 ms
+UnloadTime: 1.371720 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]: 4066 frames, [32.0 KB-64.0 KB]: 4489 frames, [64.0 KB-128.0 KB]: 838 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3972 frames, [32.0 KB-64.0 KB]: 10859 frames, [64.0 KB-128.0 KB]: 3939 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
@@ -131,12 +128,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_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
@@ -207,28 +204,28 @@ 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]: 9095 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 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 12775
+  Peak main deferred allocation count 12625
     [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]: 9393 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18770 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.3 MB
+      Peak Allocated memory 30.2 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9394 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18771 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.7 MB
+      Peak Allocated memory 24.1 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +254,13 @@ 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]: 9393 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18770 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]: 9394 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18771 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,13 +272,13 @@ 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]: 9095 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 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]: 9393 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18770 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
@@ -293,25 +290,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.6 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9394 frames
+      Peak usage frame count: [0-1.0 KB]: 18771 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]: 9394 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18771 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]: 9394 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18771 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 27.4 KB
+  Peak Allocated memory 29.2 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":1657727711838,"processId":272,"allocatedMemory":1957329,"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":3444},{"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":1657731909688,"processId":926,"allocatedMemory":1957329,"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":3444},{"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

@@ -2,256 +2,256 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.5681598782539368,
-            "min": 0.5681598782539368,
-            "max": 1.3228497505187988,
-            "count": 10
+            "value": 0.3776736259460449,
+            "min": 0.3776736259460449,
+            "max": 1.2476093769073486,
+            "count": 20
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 28271.634765625,
-            "min": 28271.634765625,
-            "max": 67941.5625,
-            "count": 10
+            "value": 18998.494140625,
+            "min": 18998.494140625,
+            "max": 62440.35546875,
+            "count": 20
         },
         "Pyramids.Step.mean": {
-            "value": 499961.0,
-            "min": 49980.0,
-            "max": 499961.0,
-            "count": 10
+            "value": 999874.0,
+            "min": 49920.0,
+            "max": 999874.0,
+            "count": 20
         },
         "Pyramids.Step.sum": {
-            "value": 499961.0,
-            "min": 49980.0,
-            "max": 499961.0,
-            "count": 10
+            "value": 999874.0,
+            "min": 49920.0,
+            "max": 999874.0,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.14217694103717804,
-            "min": -0.09073202311992645,
-            "max": 0.14217694103717804,
-            "count": 10
+            "value": 0.6256685256958008,
+            "min": -0.06844426691532135,
+            "max": 0.672815203666687,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 59.42995834350586,
-            "min": -36.474273681640625,
-            "max": 59.42995834350586,
-            "count": 10
+            "value": 292.8128662109375,
+            "min": -27.51459503173828,
+            "max": 322.9512939453125,
+            "count": 20
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.05098048597574234,
-            "min": 0.05029464140534401,
-            "max": 0.7062878608703613,
-            "count": 10
+            "value": 0.018741514533758163,
+            "min": -0.0005381633527576923,
+            "max": 0.3810485899448395,
+            "count": 20
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 21.309843063354492,
-            "min": 20.872276306152344,
-            "max": 282.51513671875,
-            "count": 10
+            "value": 8.771028518676758,
+            "min": -0.2561657428741455,
+            "max": 152.03839111328125,
+            "count": 20
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.07004182281511924,
-            "min": 0.0675196686797219,
-            "max": 0.07379435087724227,
-            "count": 10
+            "value": 0.0697640247633578,
+            "min": 0.06765343706701613,
+            "max": 0.07579705501969632,
+            "count": 20
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 1.6109619247477425,
-            "min": 0.9593265614041496,
-            "max": 1.7189425113182926,
-            "count": 10
+            "value": 1.6743365943205872,
+            "min": 0.9095646602363558,
+            "max": 1.7159414038070084,
+            "count": 20
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.008374699226239329,
-            "min": 0.0017309119011206793,
-            "max": 0.022593066516711207,
-            "count": 10
+            "value": 0.01741114089500294,
+            "min": 0.002489177529720798,
+            "max": 0.01741114089500294,
+            "count": 20
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.19261808220350457,
-            "min": 0.03634914992353427,
-            "max": 0.2937098647172457,
-            "count": 10
+            "value": 0.4178673814800705,
+            "min": 0.04729437306469516,
+            "max": 0.4178673814800705,
+            "count": 20
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 1.5007999345191308e-05,
-            "min": 1.5007999345191308e-05,
-            "max": 0.0002835668362469538,
-            "count": 10
+            "value": 7.3296975567999975e-06,
+            "min": 7.3296975567999975e-06,
+            "max": 0.00029215680261440003,
+            "count": 20
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0003451839849394001,
-            "min": 0.0003451839849394001,
-            "max": 0.0053536551154484,
-            "count": 10
+            "value": 0.00017591274136319993,
+            "min": 0.00017591274136319993,
+            "max": 0.006032718889093801,
+            "count": 20
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10500263478260871,
-            "min": 0.10500263478260871,
-            "max": 0.19452227692307694,
-            "count": 10
+            "value": 0.1024432,
+            "min": 0.1024432,
+            "max": 0.19738560000000002,
+            "count": 20
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 2.4150606000000003,
-            "min": 2.4150606000000003,
-            "max": 3.8845516,
-            "count": 10
+            "value": 2.4586368,
+            "min": 2.3686272,
+            "max": 4.3109062,
+            "count": 20
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.000509763214782609,
-            "min": 0.000509763214782609,
-            "max": 0.009452775464615384,
-            "count": 10
+            "value": 0.0002540756799999999,
+            "min": 0.0002540756799999999,
+            "max": 0.00973882144,
+            "count": 20
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.011724553940000007,
-            "min": 0.011724553940000007,
-            "max": 0.17848670484,
-            "count": 10
+            "value": 0.0060978163199999985,
+            "min": 0.0060978163199999985,
+            "max": 0.20111952938000002,
+            "count": 20
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.0341656468808651,
-            "min": 0.0341656468808651,
-            "max": 0.5372101068496704,
-            "count": 10
+            "value": 0.0150672048330307,
+            "min": 0.014632516540586948,
+            "max": 0.37728455662727356,
+            "count": 20
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.7858098745346069,
-            "min": 0.7858098745346069,
-            "max": 6.983731269836426,
-            "count": 10
+            "value": 0.3616129159927368,
+            "min": 0.35118040442466736,
+            "max": 4.527414798736572,
+            "count": 20
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 719.5441176470588,
-            "min": 719.5441176470588,
-            "max": 984.25,
-            "count": 10
+            "value": 294.874251497006,
+            "min": 276.92090395480227,
+            "max": 999.0,
+            "count": 20
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 48929.0,
-            "min": 47244.0,
-            "max": 52588.0,
-            "count": 10
+            "value": 49244.0,
+            "min": 46491.0,
+            "max": 53316.0,
+            "count": 20
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 0.51550583760528,
-            "min": -0.9018750513593355,
-            "max": 0.51550583760528,
-            "count": 10
+            "value": 1.645226325862065,
+            "min": -1.0000000521540642,
+            "max": 1.6778700413171854,
+            "count": 20
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 35.05439695715904,
-            "min": -43.29000246524811,
-            "max": 35.05439695715904,
-            "count": 10
+            "value": 274.75279641896486,
+            "min": -48.00000250339508,
+            "max": 296.9829973131418,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 0.51550583760528,
-            "min": -0.9018750513593355,
-            "max": 0.51550583760528,
-            "count": 10
+            "value": 1.645226325862065,
+            "min": -1.0000000521540642,
+            "max": 1.6778700413171854,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 35.05439695715904,
-            "min": -43.29000246524811,
-            "max": 35.05439695715904,
-            "count": 10
+            "value": 274.75279641896486,
+            "min": -48.00000250339508,
+            "max": 296.9829973131418,
+            "count": 20
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.2559640761524754,
-            "min": 0.2559640761524754,
-            "max": 8.122548788165053,
-            "count": 10
+            "value": 0.04574964659164442,
+            "min": 0.04574964659164442,
+            "max": 5.083442655702432,
+            "count": 20
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 17.405557178368326,
-            "min": 17.405557178368326,
-            "max": 389.88234183192253,
-            "count": 10
+            "value": 7.6401909808046184,
+            "min": 7.538699409909896,
+            "max": 244.00524747371674,
+            "count": 20
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 20
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 20
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1657726179",
+        "start_time_seconds": "1657728190",
         "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids_Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids_Training1 --no-graphics",
         "mlagents_version": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1657727711"
+        "end_time_seconds": "1657731909"
     },
-    "total": 1532.167608667,
+    "total": 3719.51996703,
     "count": 1,
-    "self": 0.736263854000299,
+    "self": 0.5429586899999777,
     "children": {
         "run_training.setup": {
-            "total": 0.0585323079999398,
+            "total": 0.08578315099975953,
             "count": 1,
-            "self": 0.0585323079999398
+            "self": 0.08578315099975953
         },
         "TrainerController.start_learning": {
-            "total": 1531.3728125049997,
+            "total": 3718.891225189,
             "count": 1,
-            "self": 1.2976342699912493,
+            "self": 2.896064432078674,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 10.288719579999906,
+                    "total": 5.709341595999831,
                     "count": 1,
-                    "self": 10.288719579999906
+                    "self": 5.709341595999831
                 },
                 "TrainerController.advance": {
-                    "total": 1519.6516352550088,
-                    "count": 31650,
-                    "self": 1.3194515280160886,
+                    "total": 3710.1862332859214,
+                    "count": 64352,
+                    "self": 3.083193245041457,
                     "children": {
                         "env_step": {
-                            "total": 888.927109817004,
-                            "count": 31650,
-                            "self": 813.4394815900032,
+                            "total": 2345.712429656001,
+                            "count": 64352,
+                            "self": 2182.784042892131,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 74.73825263599804,
-                                    "count": 31650,
-                                    "self": 3.7822936319912515,
+                                    "total": 161.2830565309241,
+                                    "count": 64352,
+                                    "self": 8.515540034939932,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 70.95595900400679,
-                                            "count": 31313,
-                                            "self": 15.595505347027142,
+                                            "total": 152.76751649598418,
+                                            "count": 62570,
+                                            "self": 34.58320609797693,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 55.360453656979644,
-                                                    "count": 31313,
-                                                    "self": 55.360453656979644
+                                                    "total": 118.18431039800726,
+                                                    "count": 62570,
+                                                    "self": 118.18431039800726
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7493755910027176,
-                                    "count": 31650,
+                                    "total": 1.6453302329459802,
+                                    "count": 64352,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1528.2044942590273,
-                                            "count": 31650,
+                                            "total": 3711.5316603228575,
+                                            "count": 64352,
                                             "is_parallel": true,
-                                            "self": 799.4302569030251,
+                                            "self": 1719.0149781576533,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.008049904999893442,
+                                                            "total": 0.0033231490001526254,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00595759299983456,
+                                                            "self": 0.0012802779997400648,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0020923120000588824,
+                                                                    "total": 0.0020428710004125605,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0020923120000588824
+                                                                    "self": 0.0020428710004125605
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06828021699993769,
+                                                            "total": 0.08057971700009148,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006089470000461006,
+                                                            "self": 0.0006640510000579525,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0008014960000082283,
+                                                                    "total": 0.0005635749998873507,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0008014960000082283
+                                                                    "self": 0.0005635749998873507
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.064714763999973,
+                                                                    "total": 0.07720498900016537,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.064714763999973
+                                                                    "self": 0.07720498900016537
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0021550099999103622,
+                                                                    "total": 0.002147101999980805,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005696680000255583,
+                                                                    "self": 0.000598724999690603,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001585341999884804,
+                                                                            "total": 0.001548377000290202,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001585341999884804
+                                                                            "self": 0.001548377000290202
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 728.7742373560022,
-                                                    "count": 31649,
+                                                    "total": 1992.5166821652042,
+                                                    "count": 64351,
                                                     "is_parallel": true,
-                                                    "self": 20.372478276950915,
+                                                    "self": 44.97937237126962,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 11.837199776018679,
-                                                            "count": 31649,
+                                                            "total": 28.048393197027963,
+                                                            "count": 64351,
                                                             "is_parallel": true,
-                                                            "self": 11.837199776018679
+                                                            "self": 28.048393197027963
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 632.7837335230098,
-                                                            "count": 31649,
+                                                            "total": 1782.6700106720255,
+                                                            "count": 64351,
                                                             "is_parallel": true,
-                                                            "self": 632.7837335230098
+                                                            "self": 1782.6700106720255
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 63.78082578002284,
-                                                            "count": 31649,
+                                                            "total": 136.81890592488116,
+                                                            "count": 64351,
                                                             "is_parallel": true,
-                                                            "self": 17.47754399901976,
+                                                            "self": 37.6737201008591,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 46.30328178100308,
-                                                                    "count": 253192,
+                                                                    "total": 99.14518582402206,
+                                                                    "count": 514808,
                                                                     "is_parallel": true,
-                                                                    "self": 46.30328178100308
+                                                                    "self": 99.14518582402206
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 629.4050739099888,
-                            "count": 31650,
-                            "self": 2.5038410159457953,
+                            "total": 1361.390610384879,
+                            "count": 64352,
+                            "self": 6.0017889249479595,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 112.5473704540401,
-                                    "count": 31650,
-                                    "self": 111.95928454004013,
+                                    "total": 251.1647456229298,
+                                    "count": 64352,
+                                    "self": 249.97967827492994,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.5880859139999757,
-                                            "count": 5,
-                                            "self": 0.5880859139999757
+                                            "total": 1.1850673479998477,
+                                            "count": 10,
+                                            "self": 1.1850673479998477
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 514.3538624400029,
-                                    "count": 218,
-                                    "self": 136.74705431799475,
+                                    "total": 1104.2240758370012,
+                                    "count": 456,
+                                    "self": 277.4872305620506,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 377.60680812200815,
-                                            "count": 11394,
-                                            "self": 377.60680812200815
+                                            "total": 826.7368452749506,
+                                            "count": 22851,
+                                            "self": 826.7368452749506
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.3539997780753765e-06,
+                    "total": 1.3480002962751314e-06,
                     "count": 1,
-                    "self": 1.3539997780753765e-06
+                    "self": 1.3480002962751314e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.13482204599995384,
+                    "total": 0.09958452699993359,
                     "count": 1,
-                    "self": 0.0026258959996994236,
+                    "self": 0.002081748999444244,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.13219615000025442,
+                            "total": 0.09750277800048934,
                             "count": 1,
-                            "self": 0.13219615000025442
+                            "self": 0.09750277800048934
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 199947,
-                "file_path": "results/Pyramids_Training/Pyramids/Pyramids-199947.onnx",
-                "reward": null,
-                "creation_time": 1657726780.3862202,
+                "steps": 699878,
+                "file_path": "results/Pyramids_Training1/Pyramids/Pyramids-699878.onnx",
+                "reward": 1.7179999575018883,
+                "creation_time": 1657730744.3550265,
                 "auxillary_file_paths": [
-                    "results/Pyramids_Training/Pyramids/Pyramids-199947.pt"
+                    "results/Pyramids_Training1/Pyramids/Pyramids-699878.pt"
                 ]
             },
             {
-                "steps": 299952,
-                "file_path": "results/Pyramids_Training/Pyramids/Pyramids-299952.onnx",
-                "reward": 0.16359996050596237,
-                "creation_time": 1657727083.732131,
+                "steps": 799911,
+                "file_path": "results/Pyramids_Training1/Pyramids/Pyramids-799911.onnx",
+                "reward": 1.5135713985988073,
+                "creation_time": 1657731132.6573567,
                 "auxillary_file_paths": [
-                    "results/Pyramids_Training/Pyramids/Pyramids-299952.pt"
+                    "results/Pyramids_Training1/Pyramids/Pyramids-799911.pt"
                 ]
             },
             {
-                "steps": 399927,
-                "file_path": "results/Pyramids_Training/Pyramids/Pyramids-399927.onnx",
-                "reward": 0.5923999696969986,
-                "creation_time": 1657727395.4137464,
+                "steps": 899924,
+                "file_path": "results/Pyramids_Training1/Pyramids/Pyramids-899924.onnx",
+                "reward": 1.678142832858222,
+                "creation_time": 1657731526.299883,
                 "auxillary_file_paths": [
-                    "results/Pyramids_Training/Pyramids/Pyramids-399927.pt"
+                    "results/Pyramids_Training1/Pyramids/Pyramids-899924.pt"
                 ]
             },
             {
-                "steps": 499961,
-                "file_path": "results/Pyramids_Training/Pyramids/Pyramids-499961.onnx",
-                "reward": 0.5564666241407394,
-                "creation_time": 1657727711.0006368,
+                "steps": 999874,
+                "file_path": "results/Pyramids_Training1/Pyramids/Pyramids-999874.onnx",
+                "reward": null,
+                "creation_time": 1657731909.0665789,
                 "auxillary_file_paths": [
-                    "results/Pyramids_Training/Pyramids/Pyramids-499961.pt"
+                    "results/Pyramids_Training1/Pyramids/Pyramids-999874.pt"
                 ]
             },
             {
-                "steps": 500089,
-                "file_path": "results/Pyramids_Training/Pyramids/Pyramids-500089.onnx",
-                "reward": 0.5564666241407394,
-                "creation_time": 1657727711.1552916,
+                "steps": 1000002,
+                "file_path": "results/Pyramids_Training1/Pyramids/Pyramids-1000002.onnx",
+                "reward": null,
+                "creation_time": 1657731909.188042,
                 "auxillary_file_paths": [
-                    "results/Pyramids_Training/Pyramids/Pyramids-500089.pt"
+                    "results/Pyramids_Training1/Pyramids/Pyramids-1000002.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 500089,
-            "file_path": "results/Pyramids_Training/Pyramids.onnx",
-            "reward": 0.5564666241407394,
-            "creation_time": 1657727711.1552916,
+            "steps": 1000002,
+            "file_path": "results/Pyramids_Training1/Pyramids.onnx",
+            "reward": null,
+            "creation_time": 1657731909.188042,
             "auxillary_file_paths": [
-                "results/Pyramids_Training/Pyramids/Pyramids-500089.pt"
+                "results/Pyramids_Training1/Pyramids/Pyramids-1000002.pt"
             ]
         }
     },