Fixed bash bug - mlagents-learn not found

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4348036dd0d5c6861bd2445b23f192edcfe446621e69c109af128946089888f
+oid sha256:7354700265026d0b204f8d157916bd721a01f208d280e96ebb116070f2d5c44b
 size 1417437

Pyramids/{Pyramids-1252618.onnx → Pyramids-1000082.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4348036dd0d5c6861bd2445b23f192edcfe446621e69c109af128946089888f
+oid sha256:7354700265026d0b204f8d157916bd721a01f208d280e96ebb116070f2d5c44b
 size 1417437

Pyramids/{Pyramids-1252618.pt → Pyramids-1000082.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43de801de6483535789e6e275e2873fde5ba3230cfd9d5f40548b2b7a5f13d3a
-size 8652382
+oid sha256:c65d553cb663ec3a833b5ad87422b01923361b5738c9b28bddd0eb62c1e6fa16
+size 8651427

Pyramids/{Pyramids-999994.onnx → Pyramids-499875.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:514254baaac8e22299c2a57b577a99db4d45e2aaf04426998357d35bbbe9341d
+oid sha256:0c0cf07c4bc7b96415ae53a02e0d6aa5e50c223321b0e809c0a3d09af3a72e4d
 size 1417437

Pyramids/{Pyramids-499879.pt → Pyramids-499875.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e808b57f8c1d12f54b216bc6f79416b88bb2bf300dab6c6cc26aedbd8e9d69
-size 8652382
+oid sha256:b87c77e1bf1f559175fdb710a1343b2fb50ab6dad32876aab80c6a0221b68f3b
+size 8651427

Pyramids/{Pyramids-499879.onnx → Pyramids-999954.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f524239e34ea9c75ce74b41d8944baa745d869772b2aaf6463d7478ee201857
+oid sha256:7354700265026d0b204f8d157916bd721a01f208d280e96ebb116070f2d5c44b
 size 1417437

Pyramids/Pyramids-999954.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9147fd1358b46d71b7f7b4fcabd669e3019212b3ce4c0dabb5da1fb8322e15e6
+size 8651427

Pyramids/Pyramids-999994.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:16fce4ebf2b9000204d6b00d8d9447cab722a2f59c15e67932d3d296322b1fab
-size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43de801de6483535789e6e275e2873fde5ba3230cfd9d5f40548b2b7a5f13d3a
-size 8652382
+oid sha256:c65d553cb663ec3a833b5ad87422b01923361b5738c9b28bddd0eb62c1e6fa16
+size 8651427

Pyramids/{events.out.tfevents.1658672915.410d80450fc1.212.0 → events.out.tfevents.1661155235.0f67ab6d30c4.464.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bb8d676725e407ebfb51121059b22f93d9b30285643187d2d80a6f512a3e116
-size 397091
+oid sha256:f040e61d546ed03fdfc11d17f5f37982965ada99d3400a95faf4cc814c03e72b
+size 332946

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": 3000000, "time_horizon": 128, "summary_freq": 30000, "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": 500000, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "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}

configuration.yaml

@@ -49,7 +49,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     checkpoint_interval: 500000
-    max_steps: 3000000
+    max_steps: 1000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 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] 55494 [Flags] 2 [Guid] 3747311524 [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] 55500 [Flags] 2 [Guid] 4225727653 [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
@@ -36,7 +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  0.094 seconds
+- Completed reload, in  0.114 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 +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: 0.973858 ms
+UnloadTime: 1.321830 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 +76,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 2189 frames, [32.0 KB-64.0 KB]: 16034 frames, [64.0 KB-128.0 KB]: 5280 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 4805 frames, [32.0 KB-64.0 KB]: 11876 frames, [64.0 KB-128.0 KB]: 2089 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -126,17 +126,17 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 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 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -149,7 +149,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
+      Peak Allocated Bytes 480 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -207,28 +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]: 23205 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 12856
+  Peak main deferred allocation count 12983
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      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]: 23503 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 31.0 MB
+      Peak Allocated memory 30.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 23504 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 22.9 MB
+      Peak Allocated memory 22.8 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,15 +255,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 23503 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]: 23504 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
@@ -273,15 +273,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      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]: 23205 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]: 23503 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
@@ -291,27 +291,27 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 23504 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]: 23504 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]: 23504 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 29.2 KB
+  Peak Allocated memory 29.0 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":1658675698793,"processId":224,"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":1661158307785,"processId":474,"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

@@ -2,189 +2,189 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.2899654805660248,
-            "min": 0.28584811091423035,
-            "max": 1.4236252307891846,
-            "count": 41
+            "value": 0.537936270236969,
+            "min": 0.537936270236969,
+            "max": 1.3857479095458984,
+            "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 8787.1142578125,
-            "min": 8520.560546875,
-            "max": 43187.09375,
-            "count": 41
+            "value": 16301.6201171875,
+            "min": 16301.6201171875,
+            "max": 42038.046875,
+            "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 1229997.0,
+            "value": 989974.0,
             "min": 29952.0,
-            "max": 1229997.0,
-            "count": 41
+            "max": 989974.0,
+            "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 1229997.0,
+            "value": 989974.0,
             "min": 29952.0,
-            "max": 1229997.0,
-            "count": 41
+            "max": 989974.0,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.8069287538528442,
-            "min": -0.10137598216533661,
-            "max": 0.8069287538528442,
-            "count": 41
+            "value": 0.2987557351589203,
+            "min": -0.10508545488119125,
+            "max": 0.3129414916038513,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 240.4647674560547,
-            "min": -24.330236434936523,
-            "max": 240.4647674560547,
-            "count": 41
+            "value": 77.37773895263672,
+            "min": -25.430679321289062,
+            "max": 80.42596435546875,
+            "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.013106937520205975,
-            "min": -0.01805024966597557,
-            "max": 0.4306671619415283,
-            "count": 41
+            "value": -0.016964631155133247,
+            "min": -0.016964631155133247,
+            "max": 0.3806672692298889,
+            "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -3.905867338180542,
-            "min": -4.999919414520264,
-            "max": 102.068115234375,
-            "count": 41
+            "value": -4.393839359283447,
+            "min": -4.393839359283447,
+            "max": 90.2181396484375,
+            "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06829092282174463,
-            "min": 0.06448111323734644,
-            "max": 0.07420187728008157,
-            "count": 41
+            "value": 0.06988025348853423,
+            "min": 0.06411768943503847,
+            "max": 0.07604630539601967,
+            "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9560729195044249,
-            "min": 0.4824396216002127,
-            "max": 1.0618449050622683,
-            "count": 41
+            "value": 1.0482038023280134,
+            "min": 0.5323241377721377,
+            "max": 1.0996024134733222,
+            "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.012827238258300804,
-            "min": 0.00045624834884924574,
-            "max": 0.01638201445945035,
-            "count": 41
+            "value": 0.012970652159452178,
+            "min": 0.0006412699549866713,
+            "max": 0.014323089758630992,
+            "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.17958133561621126,
-            "min": 0.004106235139643212,
-            "max": 0.2293482024323049,
-            "count": 41
+            "value": 0.19455978239178268,
+            "min": 0.008977779369813399,
+            "max": 0.2005232566208339,
+            "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 0.00017846274051243338,
-            "min": 0.00017846274051243338,
-            "max": 0.00029838354339596195,
-            "count": 41
+            "value": 7.422677525806665e-06,
+            "min": 7.422677525806665e-06,
+            "max": 0.00029515063018788575,
+            "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0024984783671740673,
-            "min": 0.0020886848037717336,
-            "max": 0.0038926744024419336,
-            "count": 41
+            "value": 0.00011134016288709997,
+            "min": 0.00011134016288709997,
+            "max": 0.0035084615305128993,
+            "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.1594875666666667,
-            "min": 0.1594875666666667,
-            "max": 0.19946118095238097,
-            "count": 41
+            "value": 0.10247419333333334,
+            "min": 0.10247419333333334,
+            "max": 0.19838354285714285,
+            "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 2.232825933333334,
-            "min": 1.3962282666666668,
-            "max": 2.797558066666667,
-            "count": 41
+            "value": 1.5371129000000001,
+            "min": 1.3886848,
+            "max": 2.5694871,
+            "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.005952807910000001,
-            "min": 0.005952807910000001,
-            "max": 0.009946171977142856,
-            "count": 41
+            "value": 0.000257171914,
+            "min": 0.000257171914,
+            "max": 0.00983851593142857,
+            "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.08333931074,
-            "min": 0.06962320384,
-            "max": 0.12977605086,
-            "count": 41
+            "value": 0.0038575787099999997,
+            "min": 0.0038575787099999997,
+            "max": 0.11697176129,
+            "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.008461430668830872,
-            "min": 0.008461430668830872,
-            "max": 0.41180092096328735,
-            "count": 41
+            "value": 0.012460886500775814,
+            "min": 0.012460886500775814,
+            "max": 0.5152274966239929,
+            "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.1184600293636322,
-            "min": 0.1184600293636322,
-            "max": 2.8826065063476562,
-            "count": 41
+            "value": 0.18691329658031464,
+            "min": 0.17502087354660034,
+            "max": 3.6065926551818848,
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 237.584,
-            "min": 237.584,
+            "value": 496.08620689655174,
+            "min": 496.08620689655174,
             "max": 999.0,
-            "count": 41
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29698.0,
+            "value": 28773.0,
             "min": 15984.0,
-            "max": 32502.0,
-            "count": 41
+            "max": 32439.0,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.746411183834076,
+            "value": 1.3372526048568256,
             "min": -1.0000000521540642,
-            "max": 1.746411183834076,
-            "count": 41
+            "max": 1.3372526048568256,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 218.3013979792595,
-            "min": -31.99920167028904,
-            "max": 218.3013979792595,
-            "count": 41
+            "value": 76.22339847683907,
+            "min": -30.469401702284813,
+            "max": 76.22339847683907,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.746411183834076,
+            "value": 1.3372526048568256,
             "min": -1.0000000521540642,
-            "max": 1.746411183834076,
-            "count": 41
+            "max": 1.3372526048568256,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 218.3013979792595,
-            "min": -31.99920167028904,
-            "max": 218.3013979792595,
-            "count": 41
+            "value": 76.22339847683907,
+            "min": -30.469401702284813,
+            "max": 76.22339847683907,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.020895628459169528,
-            "min": 0.020895628459169528,
-            "max": 8.422627033665776,
-            "count": 41
+            "value": 0.06230818303741041,
+            "min": 0.06230818303741041,
+            "max": 10.663450403138995,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 2.611953557396191,
-            "min": 2.587342332233675,
-            "max": 134.76203253865242,
-            "count": 41
+            "value": 3.5515664331323933,
+            "min": 3.5515664331323933,
+            "max": 170.61520645022392,
+            "count": 33
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 41
+            "count": 33
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 41
+            "count": 33
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1658672908",
+        "start_time_seconds": "1661155224",
         "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",
         "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": "1658675698"
+        "end_time_seconds": "1661158307"
     },
-    "total": 2790.626398085,
+    "total": 3083.676767436,
     "count": 1,
-    "self": 0.3481506959997205,
+    "self": 0.6833655189998353,
     "children": {
         "run_training.setup": {
-            "total": 0.044852698999989116,
+            "total": 0.05427349999990838,
             "count": 1,
-            "self": 0.044852698999989116
+            "self": 0.05427349999990838
         },
         "TrainerController.start_learning": {
-            "total": 2790.2333946900003,
+            "total": 3082.939128417,
             "count": 1,
-            "self": 1.8101129170158856,
+            "self": 2.4252582980629995,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 10.64714840000002,
+                    "total": 11.044875691000016,
                     "count": 1,
-                    "self": 10.64714840000002
+                    "self": 11.044875691000016
                 },
                 "TrainerController.advance": {
-                    "total": 2777.6252222529843,
-                    "count": 80700,
-                    "self": 1.9055193179219714,
+                    "total": 3069.361343868938,
+                    "count": 63433,
+                    "self": 2.6793028398874412,
                     "children": {
                         "env_step": {
-                            "total": 1844.4852667560303,
-                            "count": 80700,
-                            "self": 1707.0533900391108,
+                            "total": 1802.4806044610023,
+                            "count": 63433,
+                            "self": 1658.497047256109,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 136.47011882598073,
-                                    "count": 80700,
-                                    "self": 5.937653609954424,
+                                    "total": 142.53790752391296,
+                                    "count": 63433,
+                                    "self": 7.213905162863057,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 130.5324652160263,
-                                            "count": 78346,
-                                            "self": 44.758218357022855,
+                                            "total": 135.3240023610499,
+                                            "count": 62567,
+                                            "self": 29.596378664142776,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 85.77424685900345,
-                                                    "count": 78346,
-                                                    "self": 85.77424685900345
+                                                    "total": 105.72762369690713,
+                                                    "count": 62567,
+                                                    "self": 105.72762369690713
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.9617578909388556,
-                                    "count": 80700,
+                                    "total": 1.4456496809802957,
+                                    "count": 63433,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2785.100852380008,
-                                            "count": 80700,
+                                            "total": 3076.388358235013,
+                                            "count": 63433,
                                             "is_parallel": true,
-                                            "self": 1209.7662778620079,
+                                            "self": 1586.414721414057,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005518131000002313,
+                                                            "total": 0.009083742000029815,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.004134050999994088,
+                                                            "self": 0.0047278530000767205,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013840800000082254,
+                                                                    "total": 0.004355888999953095,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013840800000082254
+                                                                    "self": 0.004355888999953095
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06052774400001226,
+                                                            "total": 0.07994424399998934,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005405889999963165,
+                                                            "self": 0.0007682590000968048,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00047689000001582826,
+                                                                    "total": 0.0005485279998538317,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00047689000001582826
+                                                                    "self": 0.0005485279998538317
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.056748214999998936,
+                                                                    "total": 0.057014517999959935,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.056748214999998936
+                                                                    "self": 0.057014517999959935
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0027620500000011816,
+                                                                    "total": 0.021612939000078768,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00044432400000005146,
+                                                                    "self": 0.0006446339996273309,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.00231772600000113,
+                                                                            "total": 0.020968305000451437,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.00231772600000113
+                                                                            "self": 0.020968305000451437
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1575.334574518,
-                                                    "count": 80699,
+                                                    "total": 1489.973636820956,
+                                                    "count": 63432,
                                                     "is_parallel": true,
-                                                    "self": 36.3935605940203,
+                                                    "self": 40.21890103792134,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 31.00779965998197,
-                                                            "count": 80699,
+                                                            "total": 23.365737592011783,
+                                                            "count": 63432,
                                                             "is_parallel": true,
-                                                            "self": 31.00779965998197
+                                                            "self": 23.365737592011783
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1385.5735435379884,
-                                                            "count": 80699,
+                                                            "total": 1299.3704599559792,
+                                                            "count": 63432,
                                                             "is_parallel": true,
-                                                            "self": 1385.5735435379884
+                                                            "self": 1299.3704599559792
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 122.35967072600923,
-                                                            "count": 80699,
+                                                            "total": 127.0185382350437,
+                                                            "count": 63432,
                                                             "is_parallel": true,
-                                                            "self": 30.59839916308505,
+                                                            "self": 34.502453151115105,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 91.76127156292418,
-                                                                    "count": 645592,
+                                                                    "total": 92.5160850839286,
+                                                                    "count": 507456,
                                                                     "is_parallel": true,
-                                                                    "self": 91.76127156292418
+                                                                    "self": 92.5160850839286
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 931.234436179032,
-                            "count": 80700,
-                            "self": 3.438551608120406,
+                            "total": 1264.2014365680484,
+                            "count": 63433,
+                            "self": 4.966577621054967,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 211.33477325291432,
-                                    "count": 80700,
-                                    "self": 211.12194592391432,
+                                    "total": 225.00560161999533,
+                                    "count": 63433,
+                                    "self": 224.59825272099602,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.21282732899999246,
+                                            "total": 0.4073488989993166,
                                             "count": 2,
-                                            "self": 0.21282732899999246
+                                            "self": 0.4073488989993166
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 716.4611113179972,
-                                    "count": 566,
-                                    "self": 284.8564335240344,
+                                    "total": 1034.229257326998,
+                                    "count": 451,
+                                    "self": 284.0283822679801,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 431.60467779396276,
-                                            "count": 28588,
-                                            "self": 431.60467779396276
+                                            "total": 750.200875059018,
+                                            "count": 22830,
+                                            "self": 750.200875059018
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.555000380903948e-06,
+                    "total": 1.2909995348309167e-06,
                     "count": 1,
-                    "self": 1.555000380903948e-06
+                    "self": 1.2909995348309167e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1509095649998926,
+                    "total": 0.10764926799947716,
                     "count": 1,
-                    "self": 0.002334846999929141,
+                    "self": 0.0027385729990783148,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.14857471799996347,
+                            "total": 0.10491069500039885,
                             "count": 1,
-                            "self": 0.14857471799996347
+                            "self": 0.10491069500039885
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499879,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499879.onnx",
-                "reward": 0.9571999545608249,
-                "creation_time": 1658673926.2323952,
+                "steps": 499875,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499875.onnx",
+                "reward": 1.5825000256299973,
+                "creation_time": 1661156694.2841585,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499879.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499875.pt"
                 ]
             },
             {
-                "steps": 999994,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999994.onnx",
-                "reward": null,
-                "creation_time": 1658675090.9099503,
+                "steps": 999954,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999954.onnx",
+                "reward": 1.508999988436699,
+                "creation_time": 1661158307.0092275,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999994.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999954.pt"
                 ]
             },
             {
-                "steps": 1252618,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1252618.onnx",
-                "reward": null,
-                "creation_time": 1658675698.49421,
+                "steps": 1000082,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000082.onnx",
+                "reward": 1.508999988436699,
+                "creation_time": 1661158307.1401775,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1252618.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000082.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1252618,
+            "steps": 1000082,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1658675698.49421,
+            "reward": 1.508999988436699,
+            "creation_time": 1661158307.1401775,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1252618.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000082.pt"
             ]
         }
     },