pushed the model

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ef156886247a6d19920dbfa04b7390b8249852d49e969cd3d0c227f1a679b
+oid sha256:3b499480327ed61d10e0d96e719cc4b70d502f505807da93943ea36003c58f54
 size 1418184

Pyramids/Pyramids-1100011.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b499480327ed61d10e0d96e719cc4b70d502f505807da93943ea36003c58f54
+size 1418184

Pyramids/Pyramids-1100011.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56063a705aa7d980fd0eb9cb383e1fdf1f00630c94d8c9d98e4e68871aa5e16c
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2499415af25b393732809fd5a8f4609974feb19b14066a61c3a203d8d1579da5
+oid sha256:56063a705aa7d980fd0eb9cb383e1fdf1f00630c94d8c9d98e4e68871aa5e16c
 size 8650990

Pyramids/events.out.tfevents.1694051300.f5001fcc51d4.20994.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3212ba80b712dc180edac24fbbaabf5a6d6f433e4c9b0db299101b0212d31190
+size 76835

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 10000, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1100000, "time_horizon": 128, "summary_freq": 10000, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 1100000
     time_horizon: 128
     summary_freq: 10000
     threaded: 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) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55498 [Flags] 2 [Guid] 739496809 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55384 [Flags] 2 [Guid] 4098409450 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,10 +33,17 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.137 seconds
+- Completed reload, in  0.097 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
 WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
@@ -58,14 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
-WARNING: Shader Did you use #pragma only_renderers and omit this platform?
-WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
-WARNING: Shader Did you use #pragma only_renderers and omit this platform?
-WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 1.102230 ms
+UnloadTime: 0.822879 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -73,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 5523 frames, [32.0 KB-64.0 KB]: 10094 frames, [64.0 KB-128.0 KB]: 3153 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 72 frames, [32.0 KB-64.0 KB]: 1281 frames, [64.0 KB-128.0 KB]: 535 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
@@ -123,17 +123,17 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 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
@@ -183,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       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 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -204,29 +204,29 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 45 frames, [1.0 MB-2.0 MB]: 1844 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.0 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12584
+  Peak main deferred allocation count 10390
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 299 frames, [32.0 MB-64.0 MB]: 18472 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 1888 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 44.4 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 23.8 MB
+      Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames, [8.0 MB-16.0 MB]: 18770 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1889 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 9.1 MB
-      Peak Large allocation bytes 0 B
+      Peak Allocated memory 21.8 MB
+      Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -252,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18770 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1888 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 18771 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 1889 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -270,45 +270,45 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 50 frames, [1.0 MB-2.0 MB]: 1839 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 18770 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 1888 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.1 MB
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18771 frames
+      Peak usage frame count: [0-1.0 KB]: 1889 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 18771 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 1889 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 18771 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 1889 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 27.4 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":1694050035934,"processId":5400,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1694051611655,"processId":21012,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,189 +2,189 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.41048958897590637,
-            "min": 0.3764805793762207,
-            "max": 1.5856126546859741,
-            "count": 100
+            "value": 0.38012948632240295,
+            "min": 0.34338849782943726,
+            "max": 0.40935009717941284,
+            "count": 10
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 4098.328125,
-            "min": 3468.097900390625,
-            "max": 16236.673828125,
-            "count": 100
+            "value": 3795.212646484375,
+            "min": 3340.4833984375,
+            "max": 4381.68359375,
+            "count": 10
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 315.02941176470586,
+            "min": 207.93333333333334,
+            "max": 367.5769230769231,
+            "count": 10
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 10711.0,
+            "min": 6238.0,
+            "max": 11880.0,
+            "count": 10
         },
         "Pyramids.Step.mean": {
-            "value": 999955.0,
-            "min": 9984.0,
-            "max": 999955.0,
-            "count": 100
+            "value": 1099883.0,
+            "min": 1009935.0,
+            "max": 1099883.0,
+            "count": 10
         },
         "Pyramids.Step.sum": {
-            "value": 999955.0,
-            "min": 9984.0,
-            "max": 999955.0,
-            "count": 100
+            "value": 1099883.0,
+            "min": 1009935.0,
+            "max": 1099883.0,
+            "count": 10
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.534279465675354,
-            "min": -0.1399112045764923,
-            "max": 0.6590203046798706,
-            "count": 100
+            "value": 0.5743545293807983,
+            "min": 0.5323955416679382,
+            "max": 0.6492787003517151,
+            "count": 10
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 49.153709411621094,
-            "min": -11.192895889282227,
-            "max": 64.47538757324219,
-            "count": 100
+            "value": 53.98932647705078,
+            "min": 47.74177169799805,
+            "max": 61.03219985961914,
+            "count": 10
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.09428372234106064,
-            "min": -0.04922276735305786,
-            "max": 0.45385292172431946,
-            "count": 100
+            "value": 0.2917096018791199,
+            "min": 0.011541766114532948,
+            "max": 0.2917096018791199,
+            "count": 10
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 8.674102783203125,
-            "min": -4.331603527069092,
-            "max": 35.40052795410156,
-            "count": 100
+            "value": 27.420703887939453,
+            "min": 1.01567542552948,
+            "max": 27.420703887939453,
+            "count": 10
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6335199820143835,
+            "min": 1.4835151323314868,
+            "max": 1.7920666500926017,
+            "count": 10
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 57.173199370503426,
+            "min": 38.557199731469154,
+            "max": 63.70999948680401,
+            "count": 10
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6335199820143835,
+            "min": 1.4835151323314868,
+            "max": 1.7920666500926017,
+            "count": 10
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 57.173199370503426,
+            "min": 38.557199731469154,
+            "max": 63.70999948680401,
+            "count": 10
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.027908020479870694,
+            "min": 0.020018433845446756,
+            "max": 0.03462479956631016,
+            "count": 10
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 0.9767807167954743,
+            "min": 0.6005530153634027,
+            "max": 1.086131252362975,
+            "count": 10
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.07580471936768542,
-            "min": 0.060259156414152436,
-            "max": 0.08033040460351662,
-            "count": 100
+            "value": 0.06293611889705061,
+            "min": 0.06293611889705061,
+            "max": 0.07142196778440849,
+            "count": 10
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.37902359683842707,
-            "min": 0.1418350399568832,
-            "max": 0.37902359683842707,
-            "count": 100
+            "value": 0.3146805944852531,
+            "min": 0.27378643026653054,
+            "max": 0.3571098389220424,
+            "count": 10
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.017107974860118703,
-            "min": 0.00012082310121286355,
-            "max": 0.023043040805108224,
-            "count": 100
+            "value": 0.027194201620295642,
+            "min": 0.014137531273687881,
+            "max": 0.027194201620295642,
+            "count": 10
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.08553987430059351,
-            "min": 0.0004832924048514542,
-            "max": 0.11521520402554111,
-            "count": 100
+            "value": 0.13597100810147822,
+            "min": 0.06203829336057727,
+            "max": 0.13597100810147822,
+            "count": 10
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 1.37205954267999e-06,
-            "min": 1.37205954267999e-06,
-            "max": 0.0002981568006144,
-            "count": 100
+            "value": 1.4066631675090947e-06,
+            "min": 1.4066631675090947e-06,
+            "max": 2.5832955025409093e-05,
+            "count": 10
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 6.860297713399949e-06,
-            "min": 6.860297713399949e-06,
-            "max": 0.0012685266771577997,
-            "count": 100
+            "value": 7.033315837545473e-06,
+            "min": 7.033315837545473e-06,
+            "max": 0.00011633855212972727,
+            "count": 10
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10045732,
-            "min": 0.10045732,
-            "max": 0.1993856,
-            "count": 100
+            "value": 0.10046885454545454,
+            "min": 0.10046885454545454,
+            "max": 0.10861095454545455,
+            "count": 10
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 0.5022866,
-            "min": 0.39717119999999995,
-            "max": 0.9228422,
-            "count": 100
+            "value": 0.5023442727272727,
+            "min": 0.40911363636363635,
+            "max": 0.5387793636363637,
+            "count": 10
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 5.568626799999966e-05,
-            "min": 5.568626799999966e-05,
-            "max": 0.00993862144,
-            "count": 100
+            "value": 5.6838569090909224e-05,
+            "min": 5.6838569090909224e-05,
+            "max": 0.0008702343590909094,
+            "count": 10
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0002784313399999983,
-            "min": 0.0002784313399999983,
-            "max": 0.04229193577999999,
-            "count": 100
+            "value": 0.0002841928454545461,
+            "min": 0.0002841928454545461,
+            "max": 0.003924058427272728,
+            "count": 10
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.008825348690152168,
-            "min": 0.008805171586573124,
-            "max": 0.7345831394195557,
-            "count": 100
+            "value": 0.00895585585385561,
+            "min": 0.008252105675637722,
+            "max": 0.00922434777021408,
+            "count": 10
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.04412674531340599,
-            "min": 0.035220686346292496,
-            "max": 1.4691662788391113,
-            "count": 100
+            "value": 0.044779278337955475,
+            "min": 0.03300842270255089,
+            "max": 0.044779278337955475,
+            "count": 10
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 100
+            "count": 10
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 100
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 304.97058823529414,
-            "min": 272.58620689655174,
-            "max": 999.0,
-            "count": 99
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 10369.0,
-            "min": 434.0,
-            "max": 16055.0,
-            "count": 99
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.6367575618805308,
-            "min": -1.0000000521540642,
-            "max": 1.7182758383709809,
-            "count": 99
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 54.012999542057514,
-            "min": -16.000000834465027,
-            "max": 66.50599966943264,
-            "count": 99
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.6367575618805308,
-            "min": -1.0000000521540642,
-            "max": 1.7182758383709809,
-            "count": 99
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 54.012999542057514,
-            "min": -16.000000834465027,
-            "max": 66.50599966943264,
-            "count": 99
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.028584641527920736,
-            "min": 0.028379738536127012,
-            "max": 9.342119870707393,
-            "count": 99
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 0.9432931704213843,
-            "min": 0.7751224637031555,
-            "max": 149.47391793131828,
-            "count": 99
+            "count": 10
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1694047486",
+        "start_time_seconds": "1694051299",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
@@ -192,59 +192,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1694050035"
+        "end_time_seconds": "1694051611"
     },
-    "total": 2549.055736528,
+    "total": 312.35055579299933,
     "count": 1,
-    "self": 1.4347919130000264,
+    "self": 0.5329739949993382,
     "children": {
         "run_training.setup": {
-            "total": 0.044215636999979324,
+            "total": 0.041343445999700634,
             "count": 1,
-            "self": 0.044215636999979324
+            "self": 0.041343445999700634
         },
         "TrainerController.start_learning": {
-            "total": 2547.576728978,
+            "total": 311.7762383520003,
             "count": 1,
-            "self": 1.7623572191023413,
+            "self": 0.19924450402868388,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.777266338000118,
+                    "total": 4.386336599999595,
                     "count": 1,
-                    "self": 5.777266338000118
+                    "self": 4.386336599999595
                 },
                 "TrainerController.advance": {
-                    "total": 2539.9311499138976,
-                    "count": 63938,
-                    "self": 1.6722204319048615,
+                    "total": 307.0690165169726,
+                    "count": 6535,
+                    "self": 0.20457160697606014,
                     "children": {
                         "env_step": {
-                            "total": 1843.4899981179954,
-                            "count": 63938,
-                            "self": 1715.2971735599217,
+                            "total": 233.1392713410023,
+                            "count": 6535,
+                            "self": 219.1808961630286,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 127.17713206901749,
-                                    "count": 63938,
-                                    "self": 5.405393594041925,
+                                    "total": 13.843681481981548,
+                                    "count": 6535,
+                                    "self": 0.5951881189403139,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 121.77173847497556,
-                                            "count": 62569,
-                                            "self": 121.77173847497556
+                                            "total": 13.248493363041234,
+                                            "count": 6295,
+                                            "self": 13.248493363041234
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.015692489056164,
-                                    "count": 63938,
+                                    "total": 0.11469369599217316,
+                                    "count": 6535,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2541.712688632941,
-                                            "count": 63938,
+                                            "total": 310.9924918899733,
+                                            "count": 6535,
                                             "is_parallel": true,
-                                            "self": 959.3466585799147,
+                                            "self": 106.60040627197759,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002974149000010584,
+                                                            "total": 0.0017409629999747267,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007375160000719916,
+                                                            "self": 0.000532599999132799,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0022366329999385925,
+                                                                    "total": 0.0012083630008419277,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0022366329999385925
+                                                                    "self": 0.0012083630008419277
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05281416100001479,
+                                                            "total": 0.04888112699973135,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006664580000688147,
+                                                            "self": 0.0006081680003262591,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005504069999915373,
+                                                                    "total": 0.0004881449995082221,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005504069999915373
+                                                                    "self": 0.0004881449995082221
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04925045599998157,
+                                                                    "total": 0.04569420300049387,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04925045599998157
+                                                                    "self": 0.04569420300049387
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0023468399999728717,
+                                                                    "total": 0.0020906109994029975,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00040923900019151915,
+                                                                    "self": 0.00040230099966720445,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0019376009997813526,
+                                                                            "total": 0.001688309999735793,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0019376009997813526
+                                                                            "self": 0.001688309999735793
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1582.3660300530264,
-                                                    "count": 63937,
+                                                    "total": 204.3920856179957,
+                                                    "count": 6534,
                                                     "is_parallel": true,
-                                                    "self": 38.23381850596115,
+                                                    "self": 4.0366257598998345,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 25.21925831499084,
-                                                            "count": 63937,
+                                                            "total": 2.6815989520373478,
+                                                            "count": 6534,
                                                             "is_parallel": true,
-                                                            "self": 25.21925831499084
+                                                            "self": 2.6815989520373478
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1401.0151720819788,
-                                                            "count": 63937,
+                                                            "total": 185.1335607770534,
+                                                            "count": 6534,
                                                             "is_parallel": true,
-                                                            "self": 1401.0151720819788
+                                                            "self": 185.1335607770534
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 117.89778115009562,
-                                                            "count": 63937,
+                                                            "total": 12.540300129005118,
+                                                            "count": 6534,
                                                             "is_parallel": true,
-                                                            "self": 24.06693844714664,
+                                                            "self": 2.6117759709804886,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 93.83084270294898,
-                                                                    "count": 511496,
+                                                                    "total": 9.92852415802463,
+                                                                    "count": 52272,
                                                                     "is_parallel": true,
-                                                                    "self": 93.83084270294898
+                                                                    "self": 9.92852415802463
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,24 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 694.7689313639974,
-                            "count": 63938,
-                            "self": 3.2343938300055015,
+                            "total": 73.72517356899425,
+                            "count": 6535,
+                            "self": 0.3699449199912124,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 118.93065616099034,
-                                    "count": 63938,
-                                    "self": 118.65180276099022,
-                                    "children": {
-                                        "RLTrainer._checkpoint": {
-                                            "total": 0.2788534000001164,
-                                            "count": 2,
-                                            "self": 0.2788534000001164
-                                        }
-                                    }
+                                    "total": 12.995880112002851,
+                                    "count": 6535,
+                                    "self": 12.995880112002851
                                 },
                                 "_update_policy": {
-                                    "total": 572.6038813730015,
-                                    "count": 453,
-                                    "self": 368.5168697700167,
+                                    "total": 60.35934853700019,
+                                    "count": 47,
+                                    "self": 39.29569244804679,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 204.08701160298483,
-                                            "count": 22803,
-                                            "self": 204.08701160298483
+                                            "total": 21.063656088953394,
+                                            "count": 2256,
+                                            "self": 21.063656088953394
                                         }
                                     }
                                 }
@@ -376,19 +369,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.980000529845711e-07,
+                    "total": 8.859997251420282e-07,
                     "count": 1,
-                    "self": 8.980000529845711e-07
+                    "self": 8.859997251420282e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.10595460900003673,
+                    "total": 0.12163984499966318,
                     "count": 1,
-                    "self": 0.0018452890003572975,
+                    "self": 0.0017918989997269819,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.10410931999967943,
+                            "total": 0.1198479459999362,
                             "count": 1,
-                            "self": 0.10410931999967943
+                            "self": 0.1198479459999362
                         }
                     }
                 }

run_logs/training_status.json

@@ -41,15 +41,24 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-1000083.pt"
                 ]
+            },
+            {
+                "steps": 1100011,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1100011.onnx",
+                "reward": 1.6353333344062169,
+                "creation_time": 1694051611.161595,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1100011.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000083,
+            "steps": 1100011,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.648666650056839,
-            "creation_time": 1694050034.5458472,
+            "reward": 1.6353333344062169,
+            "creation_time": 1694051611.161595,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000083.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1100011.pt"
             ]
         }
     }