First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7abfeab0875ecf8ba95330c5f7018a40012a71643a951da3a82070e72e165e3
+oid sha256:bd309401e33a7aac1ee8c72c48d995688cff6e32d8379bcf889338d22680f9ac
 size 1418184

Pyramids/Pyramids-1499951.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6bf73c282f2e01acb0e6851bb12f72c23433317c57e4242621864516ecc453f
+size 1418184

Pyramids/Pyramids-1499951.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29d3fb4375a94bca5813766e7d4ec1cdc9155eb48ae826564bbb56a7ee0ce267
+size 8650990

Pyramids/Pyramids-1999991.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35938bf17b195b2a9743232a1823770b85b8dd67946754e043f5b8b397dc208c
+size 1418184

Pyramids/Pyramids-1999991.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f827ca7589e02640ead540e89b255aac9432b6e8d4989f96e9fb373c34078ae
+size 8650990

Pyramids/Pyramids-2120063.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd309401e33a7aac1ee8c72c48d995688cff6e32d8379bcf889338d22680f9ac
+size 1418184

Pyramids/Pyramids-2120063.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:872024ceffca70a40d531c53c8ea2f48da3eeb2cab0134e433adc3f1acdbd4d6
+size 8650990

Pyramids/Pyramids-499994.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4598d671fb6b5a06ba651d4f272853c4e9e84f58a2034cc6a2ef603a7438e9d
+size 1418184

Pyramids/Pyramids-499994.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1017ae8a08c5f61dd5bf4c471aba1b504808b88e7d9de8c518781ad6f18ffaad
+size 8650990

Pyramids/Pyramids-999914.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a73a8f4c358916f0da5807c035233fcf1b35d9bf521c0b2ee79e048e1fa1191f
+size 1418184

Pyramids/Pyramids-999914.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef21c2757cf0dc21163b4c57ffca2ae521ad0594c1f81479218b8eaa34fe8bdc
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802fa3852e9fc442f3bd06444d1463d0dcf4a6628a789bddc68c77f8866eb5d0
+oid sha256:872024ceffca70a40d531c53c8ea2f48da3eeb2cab0134e433adc3f1acdbd4d6
 size 8650990

Pyramids/events.out.tfevents.1688467589.e44867e6aa98.6434.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a0ed938a11477481a302c25c9825cd4c4adaed28d600cc19725cb845d5fa36
+size 660207

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": 2060000, "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", "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": 2120000, "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", "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

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 2060000
+    max_steps: 2120000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -80,7 +80,7 @@ checkpoint_settings:
   run_id: Pyramids
   initialize_from: null
   load_model: false
-  resume: true
+  resume: false
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -1,9 +1,12 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55147 [Flags] 2 [Guid] 694174503 [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] 55269 [Flags] 2 [Guid] 746995853 [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'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
+Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -33,7 +36,7 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.094 seconds
+- Completed reload, in  0.100 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -65,7 +68,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.802427 ms
+UnloadTime: 0.869673 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -73,7 +76,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 125 frames, [32.0 KB-64.0 KB]: 587 frames, [64.0 KB-128.0 KB]: 429 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 7756 frames, [32.0 KB-64.0 KB]: 21924 frames, [64.0 KB-128.0 KB]: 10085 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
@@ -146,7 +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
@@ -183,12 +186,12 @@ 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
@@ -204,28 +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]: 29 frames, [1.0 MB-2.0 MB]: 1113 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 39467 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.1 MB
+  Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 9430
+  Peak main deferred allocation count 13042
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.3 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 1141 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 39765 frames
       Requested Block Size 16.0 MB
-      Peak Block count 2
-      Peak Allocated memory 22.3 MB
+      Peak Block count 3
+      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]: 1142 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 39766 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.9 MB
+      Peak Allocated memory 23.0 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -252,15 +255,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.3 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 1141 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 39765 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]: 1142 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 39766 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -270,15 +273,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.3 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 33 frames, [1.0 MB-2.0 MB]: 1109 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 39467 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]: 1141 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 39765 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
@@ -288,27 +291,27 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.3 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 1142 frames
+      Peak usage frame count: [0-1.0 KB]: 39766 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]: 1142 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 39766 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]: 1142 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 39766 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 27.4 KB
+  Peak Allocated memory 29.2 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1688458790074,"processId":23797,"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":1688472543067,"processId":6454,"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

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.16006402671337128,
-            "min": 0.156986802816391,
-            "max": 0.16006402671337128,
-            "count": 2
+            "value": 0.18439249694347382,
+            "min": 0.15623076260089874,
+            "max": 1.438191294670105,
+            "count": 70
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 4814.72607421875,
-            "min": 1695.45751953125,
-            "max": 4814.72607421875,
-            "count": 2
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 234.7795275590551,
-            "min": 191.93333333333334,
-            "max": 234.7795275590551,
-            "count": 2
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29817.0,
-            "min": 8637.0,
-            "max": 29817.0,
-            "count": 2
+            "value": 5469.81884765625,
+            "min": 4661.92578125,
+            "max": 43628.97265625,
+            "count": 70
         },
         "Pyramids.Step.mean": {
-            "value": 2039950.0,
-            "min": 2009981.0,
-            "max": 2039950.0,
-            "count": 2
+            "value": 2099982.0,
+            "min": 29952.0,
+            "max": 2099982.0,
+            "count": 70
         },
         "Pyramids.Step.sum": {
-            "value": 2039950.0,
-            "min": 2009981.0,
-            "max": 2039950.0,
-            "count": 2
+            "value": 2099982.0,
+            "min": 29952.0,
+            "max": 2099982.0,
+            "count": 70
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.7881335020065308,
-            "min": 0.7869158983230591,
-            "max": 0.7881335020065308,
-            "count": 2
+            "value": 0.711632251739502,
+            "min": -0.099168561398983,
+            "max": 0.8245366215705872,
+            "count": 70
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 234.07565307617188,
-            "min": 76.33084106445312,
-            "max": 234.07565307617188,
-            "count": 2
+            "value": 209.21987915039062,
+            "min": -23.89962387084961,
+            "max": 249.8345947265625,
+            "count": 70
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.014494973234832287,
-            "min": 0.014494973234832287,
-            "max": 0.01644633524119854,
-            "count": 2
+            "value": 0.004840258974581957,
+            "min": -0.016620762646198273,
+            "max": 0.36599379777908325,
+            "count": 70
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 4.305006980895996,
-            "min": 1.59529447555542,
-            "max": 4.305006980895996,
-            "count": 2
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.735530696339964,
-            "min": 1.735530696339964,
-            "max": 1.8061818080869587,
-            "count": 2
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 220.41239843517542,
-            "min": 79.47199955582619,
-            "max": 220.41239843517542,
-            "count": 2
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.735530696339964,
-            "min": 1.735530696339964,
-            "max": 1.8061818080869587,
-            "count": 2
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 220.41239843517542,
-            "min": 79.47199955582619,
-            "max": 220.41239843517542,
-            "count": 2
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.018833197139507877,
-            "min": 0.016944439728500914,
-            "max": 0.018833197139507877,
-            "count": 2
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 2.3918160367175005,
-            "min": 0.7455553480540402,
-            "max": 2.3918160367175005,
-            "count": 2
+            "value": 1.4230360984802246,
+            "min": -4.670434474945068,
+            "max": 87.83850860595703,
+            "count": 70
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06691430932412566,
-            "min": 0.06691430932412566,
-            "max": 0.07264888364685855,
-            "count": 2
+            "value": 0.06790220571352394,
+            "min": 0.06467182691988708,
+            "max": 0.07316600889161864,
+            "count": 70
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9368003305377592,
-            "min": 0.2905955345874342,
-            "max": 0.9368003305377592,
-            "count": 2
+            "value": 1.0185330857028592,
+            "min": 0.5108137817221396,
+            "max": 1.0900373466218154,
+            "count": 70
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.014317989454693383,
-            "min": 0.014317989454693383,
-            "max": 0.01548235956579447,
-            "count": 2
+            "value": 0.016380924475417332,
+            "min": 0.0006232886346490559,
+            "max": 0.01723222451012892,
+            "count": 70
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.20045185236570737,
-            "min": 0.06192943826317788,
-            "max": 0.20045185236570737,
-            "count": 2
+            "value": 0.24571386713126,
+            "min": 0.006856174981139615,
+            "max": 0.24571386713126,
+            "count": 70
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 5.216530300024272e-06,
-            "min": 5.216530300024272e-06,
-            "max": 7.982827921614084e-06,
-            "count": 2
+            "value": 4.989409657650941e-06,
+            "min": 4.989409657650941e-06,
+            "max": 0.0002977125614093801,
+            "count": 70
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 7.303142420033981e-05,
-            "min": 3.193131168645634e-05,
-            "max": 7.303142420033981e-05,
-            "count": 2
+            "value": 7.484114486476412e-05,
+            "min": 7.484114486476412e-05,
+            "max": 0.003695770922793396,
+            "count": 70
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10173881067961164,
-            "min": 0.10173881067961164,
-            "max": 0.10266091019417477,
-            "count": 2
+            "value": 0.1016631037735849,
+            "min": 0.1016631037735849,
+            "max": 0.19923752021563343,
+            "count": 70
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.424343349514563,
-            "min": 0.41064364077669907,
-            "max": 1.424343349514563,
-            "count": 2
+            "value": 1.5249465566037734,
+            "min": 1.394662641509434,
+            "max": 2.6711144811320757,
+            "count": 70
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00018370718689320387,
-            "min": 0.00018370718689320387,
-            "max": 0.0002758249283980585,
-            "count": 2
+            "value": 0.00017614406698113203,
+            "min": 0.00017614406698113203,
+            "max": 0.009923828269541779,
+            "count": 70
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0025719006165048543,
-            "min": 0.001103299713592234,
-            "max": 0.0025719006165048543,
-            "count": 2
+            "value": 0.0026421610047169804,
+            "min": 0.0026421610047169804,
+            "max": 0.12320916613207546,
+            "count": 70
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.007855918258428574,
-            "min": 0.007855918258428574,
-            "max": 0.00804874673485756,
-            "count": 2
+            "value": 0.008758272975683212,
+            "min": 0.00859245378524065,
+            "max": 0.5725786089897156,
+            "count": 70
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.10998285561800003,
-            "min": 0.03219498693943024,
-            "max": 0.10998285561800003,
-            "count": 2
+            "value": 0.13137409090995789,
+            "min": 0.12029435485601425,
+            "max": 4.008050441741943,
+            "count": 70
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 272.3482142857143,
+            "min": 227.48507462686567,
+            "max": 999.0,
+            "count": 70
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30503.0,
+            "min": 15984.0,
+            "max": 32582.0,
+            "count": 70
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6754035267286596,
+            "min": -1.0000000521540642,
+            "max": 1.7564263418316841,
+            "count": 70
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 189.32059852033854,
+            "min": -31.995601639151573,
+            "max": 235.28979843854904,
+            "count": 70
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6754035267286596,
+            "min": -1.0000000521540642,
+            "max": 1.7564263418316841,
+            "count": 70
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 189.32059852033854,
+            "min": -31.995601639151573,
+            "max": 235.28979843854904,
+            "count": 70
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.024742245137000216,
+            "min": 0.021651323840115602,
+            "max": 12.01644935272634,
+            "count": 70
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.7958737004810246,
+            "min": 2.4907763985393103,
+            "max": 192.26318964362144,
+            "count": 70
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 2
+            "count": 70
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 2
+            "count": 70
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1688458624",
+        "start_time_seconds": "1688467587",
         "python_version": "3.10.12 (main, Jun  7 2023, 12:45:35) [GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --no-graphics --resume",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --no-graphics",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1688458790"
+        "end_time_seconds": "1688472543"
     },
-    "total": 165.3351730230006,
+    "total": 4955.187998482999,
     "count": 1,
-    "self": 0.48259728100128996,
+    "self": 0.49427580699830287,
     "children": {
         "run_training.setup": {
-            "total": 0.04126745499979734,
+            "total": 0.040805112000043664,
             "count": 1,
-            "self": 0.04126745499979734
+            "self": 0.040805112000043664
         },
         "TrainerController.start_learning": {
-            "total": 164.81130828699952,
+            "total": 4954.652917564001,
             "count": 1,
-            "self": 0.07856928099772631,
+            "self": 2.6767007728731187,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.059011301999817,
+                    "total": 4.310329653000053,
                     "count": 1,
-                    "self": 5.059011301999817
+                    "self": 4.310329653000053
                 },
                 "TrainerController.advance": {
-                    "total": 159.55792486200244,
-                    "count": 4008,
-                    "self": 0.08047015601277963,
+                    "total": 4947.571646521127,
+                    "count": 137240,
+                    "self": 2.830588385165356,
                     "children": {
                         "env_step": {
-                            "total": 122.07408524198672,
-                            "count": 4008,
-                            "self": 115.64559847698911,
+                            "total": 3605.0408502358705,
+                            "count": 137240,
+                            "self": 3381.735969493785,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 6.381658935021733,
-                                    "count": 4008,
-                                    "self": 0.2825198660229944,
+                                    "total": 221.686436046057,
+                                    "count": 137240,
+                                    "self": 9.579735433220094,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 6.099139068998738,
-                                            "count": 3806,
-                                            "self": 6.099139068998738
+                                            "total": 212.1067006128369,
+                                            "count": 132553,
+                                            "self": 212.1067006128369
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.046827829975882196,
-                                    "count": 4008,
+                                    "total": 1.618444696028746,
+                                    "count": 137240,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 164.38459658699776,
-                                            "count": 4008,
+                                            "total": 4944.231098039809,
+                                            "count": 137240,
                                             "is_parallel": true,
-                                            "self": 55.86290461896624,
+                                            "self": 1796.1372172009073,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.001749106000715983,
+                                                            "total": 0.004516095000099085,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005427510013760184,
+                                                            "self": 0.0032033120005507953,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0012063549993399647,
+                                                                    "total": 0.0013127829995482898,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0012063549993399647
+                                                                    "self": 0.0013127829995482898
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.08569502299997112,
+                                                            "total": 0.04744769399985671,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005558439997912501,
+                                                            "self": 0.0006106179998823791,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005375700002332451,
+                                                                    "total": 0.0004667739999604237,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005375700002332451
+                                                                    "self": 0.0004667739999604237
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.08276233699962177,
+                                                                    "total": 0.04446434500005125,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.08276233699962177
+                                                                    "self": 0.04446434500005125
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018392720003248542,
+                                                                    "total": 0.0019059569999626547,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00037271300243446603,
+                                                                    "self": 0.0003804600000876235,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014665589978903881,
+                                                                            "total": 0.0015254969998750312,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014665589978903881
+                                                                            "self": 0.0015254969998750312
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 108.52169196803152,
-                                                    "count": 4007,
+                                                    "total": 3148.0938808389014,
+                                                    "count": 137239,
                                                     "is_parallel": true,
-                                                    "self": 2.0542488840337683,
+                                                    "self": 70.63722457688209,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 1.3711916139900495,
-                                                            "count": 4007,
+                                                            "total": 46.992340410930865,
+                                                            "count": 137239,
                                                             "is_parallel": true,
-                                                            "self": 1.3711916139900495
+                                                            "self": 46.992340410930865
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 98.87827676101642,
-                                                            "count": 4007,
+                                                            "total": 2817.5013925040635,
+                                                            "count": 137239,
                                                             "is_parallel": true,
-                                                            "self": 98.87827676101642
+                                                            "self": 2817.5013925040635
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 6.217974708991278,
-                                                            "count": 4007,
+                                                            "total": 212.96292334702503,
+                                                            "count": 137239,
                                                             "is_parallel": true,
-                                                            "self": 1.2065338049815182,
+                                                            "self": 41.40697616860507,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 5.01144090400976,
-                                                                    "count": 32056,
+                                                                    "total": 171.55594717841996,
+                                                                    "count": 1097912,
                                                                     "is_parallel": true,
-                                                                    "self": 5.01144090400976
+                                                                    "self": 171.55594717841996
                                                                 }
                                                             }
                                                         }
@@ -343,24 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 37.403369464002935,
-                            "count": 4008,
-                            "self": 0.15981210298377846,
+                            "total": 1339.700207900091,
+                            "count": 137240,
+                            "self": 5.497120208967999,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 6.524042991019996,
-                                    "count": 4008,
-                                    "self": 6.524042991019996
+                                    "total": 230.6076661561185,
+                                    "count": 137240,
+                                    "self": 230.20851767111822,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.3991484850002962,
+                                            "count": 4,
+                                            "self": 0.3991484850002962
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 30.71951436999916,
-                                    "count": 28,
-                                    "self": 19.815611368988357,
+                                    "total": 1103.5954215350046,
+                                    "count": 976,
+                                    "self": 705.6789926020608,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 10.903903001010804,
-                                            "count": 1344,
-                                            "self": 10.903903001010804
+                                            "total": 397.91642893294375,
+                                            "count": 48318,
+                                            "self": 397.91642893294375
                                         }
                                     }
                                 }
@@ -369,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.90999978967011e-07,
+                    "total": 9.530003808322363e-07,
                     "count": 1,
-                    "self": 9.90999978967011e-07
+                    "self": 9.530003808322363e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.11580185099955997,
+                    "total": 0.09423966400026984,
                     "count": 1,
-                    "self": 0.0017628519990466884,
+                    "self": 0.0014097210005274974,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.11403899900051329,
+                            "total": 0.09282994299974234,
                             "count": 1,
-                            "self": 0.11403899900051329
+                            "self": 0.09282994299974234
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 1499911,
-                "file_path": "results/Pyramids/Pyramids/Pyramids-1499911.onnx",
-                "reward": 1.6514999903738499,
-                "creation_time": 1688457007.3931015,
+                "steps": 499994,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-499994.onnx",
+                "reward": 1.481999933719635,
+                "creation_time": 1688468589.1745083,
                 "auxillary_file_paths": [
-                    "results/Pyramids/Pyramids/Pyramids-1499911.pt"
+                    "results/Pyramids/Pyramids/Pyramids-499994.pt"
                 ]
             },
             {
-                "steps": 1800038,
-                "file_path": "results/Pyramids/Pyramids/Pyramids-1800038.onnx",
-                "reward": 1.806500032544136,
-                "creation_time": 1688457788.487128,
+                "steps": 999914,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-999914.onnx",
+                "reward": 1.755571403673717,
+                "creation_time": 1688469751.7272742,
                 "auxillary_file_paths": [
-                    "results/Pyramids/Pyramids/Pyramids-1800038.pt"
+                    "results/Pyramids/Pyramids/Pyramids-999914.pt"
                 ]
             },
             {
-                "steps": 1999972,
-                "file_path": "results/Pyramids/Pyramids/Pyramids-1999972.onnx",
-                "reward": 1.728285693696567,
-                "creation_time": 1688458591.2445402,
+                "steps": 1499951,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-1499951.onnx",
+                "reward": 1.6174999848008156,
+                "creation_time": 1688471000.9090316,
                 "auxillary_file_paths": [
-                    "results/Pyramids/Pyramids/Pyramids-1999972.pt"
+                    "results/Pyramids/Pyramids/Pyramids-1499951.pt"
                 ]
             },
             {
-                "steps": 2000001,
-                "file_path": "results/Pyramids/Pyramids/Pyramids-2000001.onnx",
-                "reward": 1.7267499808222055,
-                "creation_time": 1688458591.3466892,
+                "steps": 1999991,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-1999991.onnx",
+                "reward": 1.7669999996821086,
+                "creation_time": 1688472241.5793407,
                 "auxillary_file_paths": [
-                    "results/Pyramids/Pyramids/Pyramids-2000001.pt"
+                    "results/Pyramids/Pyramids/Pyramids-1999991.pt"
                 ]
             },
             {
-                "steps": 2060092,
-                "file_path": "results/Pyramids/Pyramids/Pyramids-2060092.onnx",
-                "reward": 1.7506666382153828,
-                "creation_time": 1688458789.6562772,
+                "steps": 2120063,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-2120063.onnx",
+                "reward": 1.753166638314724,
+                "creation_time": 1688472542.6334617,
                 "auxillary_file_paths": [
-                    "results/Pyramids/Pyramids/Pyramids-2060092.pt"
+                    "results/Pyramids/Pyramids/Pyramids-2120063.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2060092,
+            "steps": 2120063,
             "file_path": "results/Pyramids/Pyramids.onnx",
-            "reward": 1.7506666382153828,
-            "creation_time": 1688458789.6562772,
+            "reward": 1.753166638314724,
+            "creation_time": 1688472542.6334617,
             "auxillary_file_paths": [
-                "results/Pyramids/Pyramids/Pyramids-2060092.pt"
+                "results/Pyramids/Pyramids/Pyramids-2120063.pt"
             ]
         }
     },