First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41bda1d20cbe7c0474d91933e885780c4e74c277b7d5ba2f1afc58d1e70b3f8
+oid sha256:0433c6396e0faddd5baf63129a28785ad18411d2ff9d10ec5a92d7472fba2bee
 size 1417437

Pyramids/{Pyramids-1000086.onnx → Pyramids-1499940.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41bda1d20cbe7c0474d91933e885780c4e74c277b7d5ba2f1afc58d1e70b3f8
+oid sha256:17db8b6786a29af7a954ceee35dca5f5326172729aaf3cae1519c06603233efc
 size 1417437

Pyramids/{Pyramids-999958.pt → Pyramids-1499940.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e10ebcf9acca6a60af600461af552ffa8fa518510eb27a4e2b7dc3f2e1a551e
+oid sha256:e15a107b412d25e237b54a51d15122d294d735face37f30fdd64d609afa4c7b6
 size 8652382

Pyramids/{Pyramids-999958.onnx → Pyramids-1999930.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41bda1d20cbe7c0474d91933e885780c4e74c277b7d5ba2f1afc58d1e70b3f8
+oid sha256:0433c6396e0faddd5baf63129a28785ad18411d2ff9d10ec5a92d7472fba2bee
 size 1417437

Pyramids/{Pyramids-1000086.pt → Pyramids-1999930.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8802a935570dfdcbfe843a0d3632c2aa151b9c71a7966c63859d3a4fa678b00
+oid sha256:a29dc7b434e7a9ad529e1f3bfa43370fc050fe30c784ecc382682ea79d784351
 size 8652382

Pyramids/{Pyramids-499949.onnx → Pyramids-2000058.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc7ebabdf9798697a3b7064c55a8ce0f40d216e1e4af940bda0ece026d276fe
+oid sha256:0433c6396e0faddd5baf63129a28785ad18411d2ff9d10ec5a92d7472fba2bee
 size 1417437

Pyramids/{Pyramids-499949.pt → Pyramids-2000058.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bf3c910662dee4feb0d0a3e4322eb590e3db4f928006c35d29a317aa2099538
+oid sha256:1dd08a29ee6eb861335ccaab1d53e3ada32404be86a4e1466b3926afe5e9ddc3
 size 8652382

Pyramids/Pyramids-499982.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ffcac51f6060a878fc82dddb90ef321439e3d324da83ddb18ac67994a54730e
+size 1417437

Pyramids/Pyramids-499982.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a2a6e9a0fd3febc1002d8f28b7b0e1c955ec0066a6c6e057f6fe8056bc2972d
+size 8652382

Pyramids/Pyramids-999872.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d3de1bc2a03075df2a77e560a6f62b8479de76ab778eb2561900047556ac46
+size 1417437

Pyramids/Pyramids-999872.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bceb51e3e2a9f3baf9c49037a208b3e602692735440f40f9da579ab326f9ab96
+size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8802a935570dfdcbfe843a0d3632c2aa151b9c71a7966c63859d3a4fa678b00
+oid sha256:1dd08a29ee6eb861335ccaab1d53e3ada32404be86a4e1466b3926afe5e9ddc3
 size 8652382

Pyramids/{events.out.tfevents.1673718471.ad5a8d51f09f.26029.0 → events.out.tfevents.1673727077.c5394f0d0225.1106.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ef1866d39193b907806e7292eca3452374532a9ce1f2564ad00689ca17887d
-size 323357
+oid sha256:554964e15d0b197a0d4e438e8faf3160bf475702e9acc7f8cd341ea6bae68a39
+size 646725

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": 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": 2000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids2", "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: 1000000
+    max_steps: 2000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -75,7 +75,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: Pyramids2
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55238 [Flags] 2 [Guid] 2341039423 [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] 55437 [Flags] 2 [Guid] 3272645740 [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  0.081 seconds
+- Completed reload, in  0.080 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: 0.757411 ms
+UnloadTime: 0.934854 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]: 3279 frames, [32.0 KB-64.0 KB]: 12780 frames, [64.0 KB-128.0 KB]: 2709 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 8228 frames, [32.0 KB-64.0 KB]: 20014 frames, [64.0 KB-128.0 KB]: 9274 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
@@ -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 0 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]: 18470 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37218 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 12850
+  Peak main deferred allocation count 12989
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.6 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18768 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 37516 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.0 MB
+      Peak Allocated memory 30.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18769 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37517 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.2 MB
+      Peak Allocated memory 22.7 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 1.6 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18768 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37516 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 18769 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 37517 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 1.6 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37218 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 18768 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 37516 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
@@ -291,21 +291,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.6 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18769 frames
+      Peak usage frame count: [0-1.0 KB]: 37517 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 18769 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 37517 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 18769 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 37517 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -314,4 +314,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673720432984,"processId":26050,"allocatedMemory":1957332,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673731297462,"processId":1129,"allocatedMemory":1957332,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,256 +2,256 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.40299805998802185,
-            "min": 0.40299805998802185,
-            "max": 1.4014124870300293,
-            "count": 33
+            "value": 0.1864638477563858,
+            "min": 0.18039709329605103,
+            "max": 1.4596576690673828,
+            "count": 66
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 11993.22265625,
-            "min": 11993.22265625,
-            "max": 42513.25,
-            "count": 33
+            "value": 5528.2802734375,
+            "min": 5528.2802734375,
+            "max": 44280.17578125,
+            "count": 66
         },
         "Pyramids.Step.mean": {
-            "value": 989904.0,
+            "value": 1979960.0,
             "min": 29952.0,
-            "max": 989904.0,
-            "count": 33
+            "max": 1979960.0,
+            "count": 66
         },
         "Pyramids.Step.sum": {
-            "value": 989904.0,
+            "value": 1979960.0,
             "min": 29952.0,
-            "max": 989904.0,
-            "count": 33
+            "max": 1979960.0,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.4051125943660736,
-            "min": -0.10922247171401978,
-            "max": 0.5229744911193848,
-            "count": 33
+            "value": 0.826989471912384,
+            "min": -0.089274100959301,
+            "max": 0.826989471912384,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 107.75994873046875,
-            "min": -26.322616577148438,
-            "max": 143.8179931640625,
-            "count": 33
+            "value": 246.44287109375,
+            "min": -21.515058517456055,
+            "max": 246.44287109375,
+            "count": 66
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.017003079876303673,
-            "min": -0.017003079876303673,
-            "max": 0.4239559769630432,
-            "count": 33
+            "value": 0.0027297267224639654,
+            "min": -0.008920630440115929,
+            "max": 0.19711031019687653,
+            "count": 66
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -4.5228190422058105,
-            "min": -4.5228190422058105,
-            "max": 100.47756958007812,
-            "count": 33
+            "value": 0.8134585618972778,
+            "min": -2.4264113903045654,
+            "max": 47.50358581542969,
+            "count": 66
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06778219055628314,
-            "min": 0.06567928285525923,
-            "max": 0.07439205853399637,
-            "count": 33
+            "value": 0.06875129233646605,
+            "min": 0.06307285478865565,
+            "max": 0.07546488655295622,
+            "count": 66
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.948950667787964,
-            "min": 0.4869029261208616,
-            "max": 1.0330581829046206,
-            "count": 33
+            "value": 0.9625180927105248,
+            "min": 0.4925582814083873,
+            "max": 1.0807502812919363,
+            "count": 66
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01269014198762653,
-            "min": 0.0005814221401123449,
-            "max": 0.016170598792616724,
-            "count": 33
+            "value": 0.015489411715645387,
+            "min": 0.0007500600439720249,
+            "max": 0.01684945211209375,
+            "count": 66
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.17766198782677142,
-            "min": 0.0069285663820110865,
-            "max": 0.22638838309663414,
-            "count": 33
+            "value": 0.21685176401903541,
+            "min": 0.010500840615608348,
+            "max": 0.23589232956931247,
+            "count": 66
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.531683203757145e-06,
-            "min": 7.531683203757145e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 5.2519196779642875e-06,
+            "min": 5.2519196779642875e-06,
+            "max": 0.0002975753150939428,
+            "count": 66
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010544356485260004,
-            "min": 0.00010544356485260004,
-            "max": 0.003633566588811199,
-            "count": 33
+            "value": 7.352687549150003e-05,
+            "min": 7.352687549150003e-05,
+            "max": 0.003696399067867,
+            "count": 66
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.1025105285714286,
-            "min": 0.1025105285714286,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10175060714285715,
+            "min": 0.10175060714285715,
+            "max": 0.19919177142857142,
+            "count": 66
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4351474000000004,
-            "min": 1.3691136000000002,
-            "max": 2.6111888000000003,
-            "count": 33
+            "value": 1.4245085000000002,
+            "min": 1.3943424,
+            "max": 2.6215241,
+            "count": 66
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002608018042857144,
-            "min": 0.0002608018042857144,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 0.0001848856535714286,
+            "min": 0.0001848856535714286,
+            "max": 0.009919257965714285,
+            "count": 66
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0036512252600000013,
-            "min": 0.0036512252600000013,
-            "max": 0.12113776111999999,
-            "count": 33
+            "value": 0.00258839915,
+            "min": 0.00258839915,
+            "max": 0.12322008669999998,
+            "count": 66
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.016093267127871513,
-            "min": 0.016093267127871513,
-            "max": 0.5611046552658081,
-            "count": 33
+            "value": 0.008282682858407497,
+            "min": 0.00788664910942316,
+            "max": 0.3117840588092804,
+            "count": 66
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.2253057360649109,
-            "min": 0.2253057360649109,
-            "max": 3.927732467651367,
-            "count": 33
+            "value": 0.11595755815505981,
+            "min": 0.1104130819439888,
+            "max": 2.182488441467285,
+            "count": 66
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 467.86567164179104,
-            "min": 385.7792207792208,
+            "value": 205.09420289855072,
+            "min": 205.09420289855072,
             "max": 999.0,
-            "count": 33
+            "count": 66
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31347.0,
+            "value": 28303.0,
             "min": 15984.0,
-            "max": 33050.0,
-            "count": 33
+            "max": 32875.0,
+            "count": 66
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.3546211843689282,
+            "value": 1.7804086732043736,
             "min": -1.0000000521540642,
-            "max": 1.5615599763579666,
-            "count": 33
+            "max": 1.7804086732043736,
+            "count": 66
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 89.40499816834927,
-            "min": -32.000001668930054,
-            "max": 124.92479810863733,
-            "count": 33
+            "value": 245.69639690220356,
+            "min": -30.581801749765873,
+            "max": 245.69639690220356,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.3546211843689282,
+            "value": 1.7804086732043736,
             "min": -1.0000000521540642,
-            "max": 1.5615599763579666,
-            "count": 33
+            "max": 1.7804086732043736,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 89.40499816834927,
-            "min": -32.000001668930054,
-            "max": 124.92479810863733,
-            "count": 33
+            "value": 245.69639690220356,
+            "min": -30.581801749765873,
+            "max": 245.69639690220356,
+            "count": 66
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.07681645221556678,
-            "min": 0.06602242748330112,
-            "max": 11.627755515277386,
-            "count": 33
+            "value": 0.0178303539950571,
+            "min": 0.0178303539950571,
+            "max": 6.077938006259501,
+            "count": 66
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 5.0698858462274075,
-            "min": 4.687592351314379,
-            "max": 186.04408824443817,
-            "count": 33
+            "value": 2.4605888513178797,
+            "min": 2.452773006472853,
+            "max": 97.24700810015202,
+            "count": 66
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 66
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 66
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673718468",
+        "start_time_seconds": "1673727071",
         "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids2 --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": "1673720433"
+        "end_time_seconds": "1673731297"
     },
-    "total": 1964.5429992260006,
+    "total": 4226.010252202,
     "count": 1,
-    "self": 0.4293955789999018,
+    "self": 0.44766875200002687,
     "children": {
         "run_training.setup": {
-            "total": 0.10435534800035384,
+            "total": 0.11084765500001481,
             "count": 1,
-            "self": 0.10435534800035384
+            "self": 0.11084765500001481
         },
         "TrainerController.start_learning": {
-            "total": 1964.0092482990003,
+            "total": 4225.451735795,
             "count": 1,
-            "self": 1.2094459469817593,
+            "self": 2.5331752540687376,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.2489533629996,
+                    "total": 9.845023167999983,
                     "count": 1,
-                    "self": 6.2489533629996
+                    "self": 9.845023167999983
                 },
                 "TrainerController.advance": {
-                    "total": 1956.4659830810187,
-                    "count": 63661,
-                    "self": 1.2463982330127692,
+                    "total": 4212.983398691931,
+                    "count": 129362,
+                    "self": 2.5400182918338032,
                     "children": {
                         "env_step": {
-                            "total": 1304.886530458035,
-                            "count": 63661,
-                            "self": 1206.8164330800191,
+                            "total": 2900.859631812995,
+                            "count": 129362,
+                            "self": 2693.850423617993,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 97.3300184299851,
-                                    "count": 63661,
-                                    "self": 4.037697418992138,
+                                    "total": 205.41543536902603,
+                                    "count": 129362,
+                                    "self": 8.252066621979282,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 93.29232101099296,
-                                            "count": 62562,
-                                            "self": 31.825975176009706,
+                                            "total": 197.16336874704675,
+                                            "count": 125055,
+                                            "self": 66.38677600709593,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 61.46634583498326,
-                                                    "count": 62562,
-                                                    "self": 61.46634583498326
+                                                    "total": 130.77659273995081,
+                                                    "count": 125055,
+                                                    "self": 130.77659273995081
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.740078948030714,
-                                    "count": 63661,
+                                    "total": 1.593772825975833,
+                                    "count": 129362,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1959.7529777540158,
-                                            "count": 63661,
+                                            "total": 4218.348804893989,
+                                            "count": 129362,
                                             "is_parallel": true,
-                                            "self": 846.7449909199968,
+                                            "self": 1722.2017308919421,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0017747299998518429,
+                                                            "total": 0.006028434999990395,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006037510011083214,
+                                                            "self": 0.0036583659999962492,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0011709789987435215,
+                                                                    "total": 0.002370068999994146,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0011709789987435215
+                                                                    "self": 0.002370068999994146
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.045615682999596174,
+                                                            "total": 0.09690124799999467,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005069059989182279,
+                                                            "self": 0.001299773999988929,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00042852699971263064,
+                                                                    "total": 0.00043830500001718065,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00042852699971263064
+                                                                    "self": 0.00043830500001718065
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.043131924000590516,
+                                                                    "total": 0.09259949899998787,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.043131924000590516
+                                                                    "self": 0.09259949899998787
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0015483260003748,
+                                                                    "total": 0.002563670000000684,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00040191800053435145,
+                                                                    "self": 0.0004910740000241276,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0011464079998404486,
+                                                                            "total": 0.0020725959999765564,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0011464079998404486
+                                                                            "self": 0.0020725959999765564
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1113.007986834019,
-                                                    "count": 63660,
+                                                    "total": 2496.147074002047,
+                                                    "count": 129361,
                                                     "is_parallel": true,
-                                                    "self": 27.196974964067522,
+                                                    "self": 55.516251133009064,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 22.064952126018397,
-                                                            "count": 63660,
+                                                            "total": 43.444309489002165,
+                                                            "count": 129361,
                                                             "is_parallel": true,
-                                                            "self": 22.064952126018397
+                                                            "self": 43.444309489002165
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 966.8633874330417,
-                                                            "count": 63660,
+                                                            "total": 2215.311333026045,
+                                                            "count": 129361,
                                                             "is_parallel": true,
-                                                            "self": 966.8633874330417
+                                                            "self": 2215.311333026045
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 96.8826723108914,
-                                                            "count": 63660,
+                                                            "total": 181.8751803539908,
+                                                            "count": 129361,
                                                             "is_parallel": true,
-                                                            "self": 20.902204680856812,
+                                                            "self": 43.05065154167369,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 75.98046763003458,
-                                                                    "count": 509280,
+                                                                    "total": 138.8245288123171,
+                                                                    "count": 1034888,
                                                                     "is_parallel": true,
-                                                                    "self": 75.98046763003458
+                                                                    "self": 138.8245288123171
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 650.333054389971,
-                            "count": 63661,
-                            "self": 2.1317321120423003,
+                            "total": 1309.5837485871023,
+                            "count": 129362,
+                            "self": 5.0889969221204865,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 139.28366888392975,
-                                    "count": 63661,
-                                    "self": 139.09700942092968,
+                                    "total": 287.4317184629816,
+                                    "count": 129362,
+                                    "self": 287.045639336981,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.18665946300006908,
-                                            "count": 2,
-                                            "self": 0.18665946300006908
+                                            "total": 0.38607912600059535,
+                                            "count": 4,
+                                            "self": 0.38607912600059535
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 508.917653393999,
-                                    "count": 450,
-                                    "self": 200.29386315711963,
+                                    "total": 1017.0630332020003,
+                                    "count": 924,
+                                    "self": 386.5747298649984,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 308.62379023687936,
-                                            "count": 22815,
-                                            "self": 308.62379023687936
+                                            "total": 630.4883033370019,
+                                            "count": 45600,
+                                            "self": 630.4883033370019
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.140003385255113e-07,
+                    "total": 8.200004231184721e-07,
                     "count": 1,
-                    "self": 9.140003385255113e-07
+                    "self": 8.200004231184721e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08486499399987224,
+                    "total": 0.09013786099967547,
                     "count": 1,
-                    "self": 0.0013775400002487004,
+                    "self": 0.0014619029998357291,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08348745399962354,
+                            "total": 0.08867595799983974,
                             "count": 1,
-                            "self": 0.08348745399962354
+                            "self": 0.08867595799983974
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499949,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499949.onnx",
-                "reward": null,
-                "creation_time": 1673719377.4944565,
+                "steps": 499982,
+                "file_path": "results/Pyramids2/Pyramids/Pyramids-499982.onnx",
+                "reward": -0.9992000460624695,
+                "creation_time": 1673727998.2577353,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499949.pt"
+                    "results/Pyramids2/Pyramids/Pyramids-499982.pt"
                 ]
             },
             {
-                "steps": 999958,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999958.onnx",
-                "reward": 1.5329999774694443,
-                "creation_time": 1673720432.5050364,
+                "steps": 999872,
+                "file_path": "results/Pyramids2/Pyramids/Pyramids-999872.onnx",
+                "reward": 1.7529999166727066,
+                "creation_time": 1673729037.8547082,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999958.pt"
+                    "results/Pyramids2/Pyramids/Pyramids-999872.pt"
                 ]
             },
             {
-                "steps": 1000086,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000086.onnx",
-                "reward": 1.5329999774694443,
-                "creation_time": 1673720432.6036575,
+                "steps": 1499940,
+                "file_path": "results/Pyramids2/Pyramids/Pyramids-1499940.onnx",
+                "reward": 1.1880399972200393,
+                "creation_time": 1673730143.4313874,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000086.pt"
+                    "results/Pyramids2/Pyramids/Pyramids-1499940.pt"
+                ]
+            },
+            {
+                "steps": 1999930,
+                "file_path": "results/Pyramids2/Pyramids/Pyramids-1999930.onnx",
+                "reward": 1.8914285429886408,
+                "creation_time": 1673731296.9604864,
+                "auxillary_file_paths": [
+                    "results/Pyramids2/Pyramids/Pyramids-1999930.pt"
+                ]
+            },
+            {
+                "steps": 2000058,
+                "file_path": "results/Pyramids2/Pyramids/Pyramids-2000058.onnx",
+                "reward": 1.8914285429886408,
+                "creation_time": 1673731297.064203,
+                "auxillary_file_paths": [
+                    "results/Pyramids2/Pyramids/Pyramids-2000058.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000086,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.5329999774694443,
-            "creation_time": 1673720432.6036575,
+            "steps": 2000058,
+            "file_path": "results/Pyramids2/Pyramids.onnx",
+            "reward": 1.8914285429886408,
+            "creation_time": 1673731297.064203,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000086.pt"
+                "results/Pyramids2/Pyramids/Pyramids-2000058.pt"
             ]
         }
     },