Third Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee5d300cec62072c62d917865ec940ca4328b80b2bea391c89e5859ed1f6a4f9
+oid sha256:bf041c5c5b57c49cbd0372442c5e4499b7769bba5b85a70459478c330e2130e7
 size 1418184

Pyramids/{Pyramids-1000001.onnx → Pyramids-1499975.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee5d300cec62072c62d917865ec940ca4328b80b2bea391c89e5859ed1f6a4f9
+oid sha256:c01e4f602cb06f689bf971ac02ec2beb0ffeb932aee334e607114c8ddd965851
 size 1418184

Pyramids/{Pyramids-999873.pt → Pyramids-1499975.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc1b7b3003e30075e170cc94c61d18935441403bfd29c8d4ab6e8217af4d5da8
+oid sha256:e33021963f45e63fb58c7cc6709fb0d00b4f930bf9b86026c39bbba2d51a7207
 size 8650990

Pyramids/{Pyramids-999873.onnx → Pyramids-1999941.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee5d300cec62072c62d917865ec940ca4328b80b2bea391c89e5859ed1f6a4f9
+oid sha256:b0fc13c42b6f407e5480d36e4cf5dd9d48126c24e7d0229c4c224fba56a9372b
 size 1418184

Pyramids/{Pyramids-1000001.pt → Pyramids-1999941.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb99e37e293916adc28a0765cd97919dcd7f4536cac52e0252456ae7423863f
+oid sha256:113a9e9751f10d07c0b5a7aa891a5eeb5ec60917771a88b7f2ede79197aef250
 size 8650990

Pyramids/{Pyramids-499959.onnx → Pyramids-2499893.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ba7b79d6d14b91966e35ba5cd9a423c75f6b2be8469baac6f3ce8bf30bdc1c7
+oid sha256:728a0ede8577dd285e347817a44f509be31e7bdbf774b71679b8ae24cd307f75
 size 1418184

Pyramids/{Pyramids-499959.pt → Pyramids-2499893.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfb87bce600c670a847ef2cb7f36d127b6359253849f64c64853d65073313128
+oid sha256:9f8a6a2f61c07692f74b4664c2b15ac825d9da52580264d5d3e09848673df924
 size 8650990

Pyramids/Pyramids-2999891.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf041c5c5b57c49cbd0372442c5e4499b7769bba5b85a70459478c330e2130e7
+size 1418184

Pyramids/Pyramids-2999891.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc322e64b709d01cfb3ea283e5f0565605a59e28fb6889e4883c1296b88fba7
+size 8650990

Pyramids/Pyramids-3000019.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf041c5c5b57c49cbd0372442c5e4499b7769bba5b85a70459478c330e2130e7
+size 1418184

Pyramids/Pyramids-3000019.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7dcd50d24028c9c536351e4a838157e1bb983b5590d1a576be02c41fd7774c9
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb99e37e293916adc28a0765cd97919dcd7f4536cac52e0252456ae7423863f
+oid sha256:b7dcd50d24028c9c536351e4a838157e1bb983b5590d1a576be02c41fd7774c9
 size 8650990

Pyramids/events.out.tfevents.1681650083.af77deb9154e.15960.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e6643cc18964c86fa90bab05ed18fa19ecc32b974f7e88182a0bc7f8f6389d
+size 1423

Pyramids/events.out.tfevents.1681650127.af77deb9154e.16200.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b07304af8ab2655e73c05b08be697bdcd3e0ec1209cb39c642e0370a78b78333
+size 546316

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": 0.02, "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": 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}
+{"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": 3000000, "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}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
           deterministic: false
       rnd:
         gamma: 0.99
-        strength: 0.02
+        strength: 0.01
         network_settings:
           normalize: false
           hidden_units: 64
@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 3000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -80,7 +80,7 @@ checkpoint_settings:
   run_id: Pyramids
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 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] 55318 [Flags] 2 [Guid] 4231710299 [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] 55032 [Flags] 2 [Guid] 3631989359 [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
@@ -36,7 +33,7 @@ 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  0.089 seconds
+- Completed reload, in  0.136 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -68,7 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 1.267351 ms
+UnloadTime: 1.208494 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 6660 frames, [32.0 KB-64.0 KB]: 9388 frames, [64.0 KB-128.0 KB]: 2722 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1802 frames, [32.0 KB-64.0 KB]: 23063 frames, [64.0 KB-128.0 KB]: 12655 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -126,7 +123,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -136,7 +133,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 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
@@ -149,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
+      Peak Allocated Bytes 480 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 80 frames, [1.0 MB-2.0 MB]: 37441 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12502
+  Peak main deferred allocation count 12540
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18770 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 37520 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 29.3 MB
+      Peak Block count 2
+      Peak Allocated memory 25.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18771 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37521 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 24.5 MB
+      Peak Allocated memory 22.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,15 +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 1.4 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]: 37520 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]: 37521 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,45 +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 1.4 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]: 79 frames, [1.0 MB-2.0 MB]: 37442 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]: 37520 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 2
-      Peak Allocated memory 4.7 MB
+      Peak Block count 1
+      Peak Allocated memory 3.9 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 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18771 frames
+      Peak usage frame count: [0-1.0 KB]: 37521 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]: 37521 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]: 37521 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 29.1 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":1681649600324,"processId":3492,"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":1681655453133,"processId":16220,"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": 0.4559151828289032,
-            "min": 0.4422323703765869,
-            "max": 1.4052366018295288,
-            "count": 33
+            "value": 0.18592286109924316,
+            "min": 0.17794272303581238,
+            "max": 0.48007693886756897,
+            "count": 67
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 13582.625,
-            "min": 13274.046875,
-            "max": 42629.2578125,
-            "count": 33
+            "value": 5631.2314453125,
+            "min": 5363.9052734375,
+            "max": 14525.2080078125,
+            "count": 67
         },
         "Pyramids.Step.mean": {
-            "value": 989988.0,
-            "min": 29952.0,
-            "max": 989988.0,
-            "count": 33
+            "value": 2999891.0,
+            "min": 1019928.0,
+            "max": 2999891.0,
+            "count": 67
         },
         "Pyramids.Step.sum": {
-            "value": 989988.0,
-            "min": 29952.0,
-            "max": 989988.0,
-            "count": 33
+            "value": 2999891.0,
+            "min": 1019928.0,
+            "max": 2999891.0,
+            "count": 67
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.48993533849716187,
-            "min": -0.11382244527339935,
-            "max": 0.511127233505249,
-            "count": 33
+            "value": 0.8583548069000244,
+            "min": 0.4942023456096649,
+            "max": 0.8688791990280151,
+            "count": 67
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 134.24227905273438,
-            "min": -27.431209564208984,
-            "max": 141.0711212158203,
-            "count": 33
+            "value": 265.23162841796875,
+            "min": 108.88697814941406,
+            "max": 270.221435546875,
+            "count": 67
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.029282841831445694,
-            "min": 0.029282841831445694,
-            "max": 0.5828818082809448,
-            "count": 33
+            "value": 0.02107888273894787,
+            "min": -0.009596453979611397,
+            "max": 0.07375943660736084,
+            "count": 67
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 8.02349853515625,
-            "min": 8.02349853515625,
-            "max": 139.89163208007812,
-            "count": 33
+            "value": 6.5133748054504395,
+            "min": -2.7253928184509277,
+            "max": 13.645496368408203,
+            "count": 67
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 196.27450980392157,
+            "min": 196.27450980392157,
+            "max": 414.6756756756757,
+            "count": 67
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30030.0,
+            "min": 15649.0,
+            "max": 31792.0,
+            "count": 67
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7904402501397318,
+            "min": 1.4484246693275593,
+            "max": 1.7904402501397318,
+            "count": 67
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 275.7277985215187,
+            "min": 92.35099902749062,
+            "max": 275.7277985215187,
+            "count": 67
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7904402501397318,
+            "min": 1.4484246693275593,
+            "max": 1.7904402501397318,
+            "count": 67
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 275.7277985215187,
+            "min": 92.35099902749062,
+            "max": 275.7277985215187,
+            "count": 67
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.017876258854387258,
+            "min": 0.017876258854387258,
+            "max": 0.06815792065321442,
+            "count": 67
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.752943863575638,
+            "min": 2.515744366814033,
+            "max": 5.043686128337868,
+            "count": 67
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06744790576132281,
-            "min": 0.06498703005743546,
-            "max": 0.07305000646628279,
-            "count": 33
+            "value": 0.07133124608296056,
+            "min": 0.06443350202688534,
+            "max": 0.07196596014220137,
+            "count": 67
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9442706806585194,
-            "min": 0.488342339750018,
-            "max": 1.0373851726608871,
-            "count": 33
+            "value": 0.9986374451614477,
+            "min": 0.638755505462862,
+            "max": 1.0680313948347855,
+            "count": 67
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.014664451570189113,
-            "min": 0.0011588689386030318,
-            "max": 0.015088778200653656,
-            "count": 33
+            "value": 0.01600719058739591,
+            "min": 0.011874273438089791,
+            "max": 0.016545076395143007,
+            "count": 67
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.20530232198264758,
-            "min": 0.012988580887551882,
-            "max": 0.21130263393085139,
-            "count": 33
+            "value": 0.22410066822354277,
+            "min": 0.11781841344468286,
+            "max": 0.2443678327562178,
+            "count": 67
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.525597491499999e-06,
-            "min": 7.525597491499999e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 1.4816852204238088e-06,
+            "min": 1.4816852204238088e-06,
+            "max": 0.0001989477114618852,
+            "count": 67
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010535836488099998,
-            "min": 0.00010535836488099998,
-            "max": 0.003633921488692899,
-            "count": 33
+            "value": 2.0743593085933322e-05,
+            "min": 2.0743593085933322e-05,
+            "max": 0.0028125587624806,
+            "count": 67
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10250849999999999,
-            "min": 0.10250849999999999,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10049386190476192,
+            "min": 0.10049386190476192,
+            "max": 0.1663158925925926,
+            "count": 67
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4351189999999998,
-            "min": 1.3691136000000002,
-            "max": 2.6113071,
-            "count": 33
+            "value": 1.4069140666666669,
+            "min": 1.4069140666666669,
+            "max": 2.4375194000000002,
+            "count": 67
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00026059915000000003,
-            "min": 0.00026059915000000003,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 5.933680428571425e-05,
+            "min": 5.933680428571425e-05,
+            "max": 0.006634957670000001,
+            "count": 67
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0036483881000000007,
-            "min": 0.0036483881000000007,
-            "max": 0.12114957929,
-            "count": 33
+            "value": 0.0008307152599999995,
+            "min": 0.0008307152599999995,
+            "max": 0.09380818806,
+            "count": 67
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.016887223348021507,
-            "min": 0.016887223348021507,
-            "max": 0.4436214566230774,
-            "count": 33
+            "value": 0.008710493333637714,
+            "min": 0.008176642470061779,
+            "max": 0.016550308093428612,
+            "count": 67
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.236421138048172,
-            "min": 0.236421138048172,
-            "max": 3.1053502559661865,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 376.775,
-            "min": 376.2470588235294,
-            "max": 999.0,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30142.0,
-            "min": 15984.0,
-            "max": 32920.0,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.5414419560520738,
-            "min": -1.0000000521540642,
-            "max": 1.5766776216380736,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 124.85679844021797,
-            "min": -32.000001668930054,
-            "max": 134.01759783923626,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.5414419560520738,
-            "min": -1.0000000521540642,
-            "max": 1.5766776216380736,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 124.85679844021797,
-            "min": -32.000001668930054,
-            "max": 134.01759783923626,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.13358603501448085,
-            "min": 0.13358603501448085,
-            "max": 15.834431545808911,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 10.82046883617295,
-            "min": 9.927237732510548,
-            "max": 253.35090473294258,
-            "count": 33
+            "value": 0.12194690853357315,
+            "min": 0.11447300016880035,
+            "max": 0.22358304262161255,
+            "count": 67
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 67
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 67
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1681647204",
+        "start_time_seconds": "1681650125",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --no-graphics --resume",
         "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": "1681649600"
+        "end_time_seconds": "1681655453"
     },
-    "total": 2396.1113926949997,
+    "total": 5327.478407201999,
     "count": 1,
-    "self": 0.909659716999613,
+    "self": 0.47530855699915264,
     "children": {
         "run_training.setup": {
-            "total": 0.11602401300001475,
+            "total": 0.20567490999974325,
             "count": 1,
-            "self": 0.11602401300001475
+            "self": 0.20567490999974325
         },
         "TrainerController.start_learning": {
-            "total": 2395.085708965,
+            "total": 5326.797423735001,
             "count": 1,
-            "self": 1.996679792026498,
+            "self": 3.591834799179196,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.098378780999951,
+                    "total": 4.933868087000064,
                     "count": 1,
-                    "self": 4.098378780999951
+                    "self": 4.933868087000064
                 },
                 "TrainerController.advance": {
-                    "total": 2388.830204293973,
-                    "count": 63738,
-                    "self": 2.0129098109368897,
+                    "total": 5318.175934921824,
+                    "count": 131163,
+                    "self": 3.8776282649005225,
                     "children": {
                         "env_step": {
-                            "total": 1743.9614275100366,
-                            "count": 63738,
-                            "self": 1605.7994242030586,
+                            "total": 4059.7783762618624,
+                            "count": 131163,
+                            "self": 3808.3597831870793,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 136.91944303600337,
-                                    "count": 63738,
-                                    "self": 5.6998883750188725,
+                                    "total": 249.27971572703837,
+                                    "count": 131163,
+                                    "self": 10.687992939127525,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 131.2195546609845,
-                                            "count": 62569,
-                                            "self": 131.2195546609845
+                                            "total": 238.59172278791084,
+                                            "count": 125069,
+                                            "self": 238.59172278791084
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.2425602709747636,
-                                    "count": 63738,
+                                    "total": 2.1388773477447103,
+                                    "count": 131163,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2388.6352776790027,
-                                            "count": 63738,
+                                            "total": 5314.536858009837,
+                                            "count": 131163,
                                             "is_parallel": true,
-                                            "self": 921.8071001679627,
+                                            "self": 1765.9769558398916,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.006126612000002751,
+                                                            "total": 0.003035013000044273,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.004685610000251472,
+                                                            "self": 0.0009488090004197147,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001441001999751279,
+                                                                    "total": 0.0020862039996245585,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001441001999751279
+                                                                    "self": 0.0020862039996245585
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.051761601999942286,
+                                                            "total": 0.05871273299999302,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006463089998760552,
+                                                            "self": 0.0005845680002494191,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005826740000429709,
+                                                                    "total": 0.000594266999996762,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005826740000429709
+                                                                    "self": 0.000594266999996762
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.048374417999980324,
+                                                                    "total": 0.05551312199986569,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.048374417999980324
+                                                                    "self": 0.05551312199986569
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0021582010000429364,
+                                                                    "total": 0.0020207759998811525,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005100459999312079,
+                                                                    "self": 0.0004644770001505094,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0016481550001117284,
+                                                                            "total": 0.0015562989997306431,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0016481550001117284
+                                                                            "self": 0.0015562989997306431
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1466.82817751104,
-                                                    "count": 63737,
+                                                    "total": 3548.559902169945,
+                                                    "count": 131162,
                                                     "is_parallel": true,
-                                                    "self": 36.63106474803635,
+                                                    "self": 69.79849993719927,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 26.225539284004867,
-                                                            "count": 63737,
+                                                            "total": 52.09461211420057,
+                                                            "count": 131162,
                                                             "is_parallel": true,
-                                                            "self": 26.225539284004867
+                                                            "self": 52.09461211420057
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1293.5296550399603,
-                                                            "count": 63737,
+                                                            "total": 3209.5752868965565,
+                                                            "count": 131162,
                                                             "is_parallel": true,
-                                                            "self": 1293.5296550399603
+                                                            "self": 3209.5752868965565
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 110.44191843903843,
-                                                            "count": 63737,
+                                                            "total": 217.09150322198866,
+                                                            "count": 131162,
                                                             "is_parallel": true,
-                                                            "self": 24.89603632997739,
+                                                            "self": 48.66155478534802,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 85.54588210906104,
-                                                                    "count": 509896,
+                                                                    "total": 168.42994843664064,
+                                                                    "count": 1049296,
                                                                     "is_parallel": true,
-                                                                    "self": 85.54588210906104
+                                                                    "self": 168.42994843664064
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 642.8558669729996,
-                            "count": 63738,
-                            "self": 3.6148124689850647,
+                            "total": 1254.5199303950603,
+                            "count": 131163,
+                            "self": 6.673967917902701,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 118.86801613701584,
-                                    "count": 63738,
-                                    "self": 118.53411737401541,
+                                    "total": 236.89730079215633,
+                                    "count": 131163,
+                                    "self": 236.4198225511559,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.333898763000434,
-                                            "count": 2,
-                                            "self": 0.333898763000434
+                                            "total": 0.47747824100042635,
+                                            "count": 4,
+                                            "self": 0.47747824100042635
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 520.3730383669987,
-                                    "count": 450,
-                                    "self": 331.7025403050093,
+                                    "total": 1010.9486616850013,
+                                    "count": 946,
+                                    "self": 641.6979436258766,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 188.6704980619894,
-                                            "count": 22770,
-                                            "self": 188.6704980619894
+                                            "total": 369.25071805912467,
+                                            "count": 45543,
+                                            "self": 369.25071805912467
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.3459998626785818e-06,
+                    "total": 1.0539988579694182e-06,
                     "count": 1,
-                    "self": 1.3459998626785818e-06
+                    "self": 1.0539988579694182e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.16044475200033048,
+                    "total": 0.09578487299950211,
                     "count": 1,
-                    "self": 0.0020525010004348587,
+                    "self": 0.0017574430003151065,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.15839225099989562,
+                            "total": 0.094027429999187,
                             "count": 1,
-                            "self": 0.15839225099989562
+                            "self": 0.094027429999187
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499959,
-                "file_path": "results/Pyramids/Pyramids/Pyramids-499959.onnx",
-                "reward": null,
-                "creation_time": 1681648335.0146089,
+                "steps": 1499975,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-1499975.onnx",
+                "reward": 1.5349999765555065,
+                "creation_time": 1681651468.6746144,
                 "auxillary_file_paths": [
-                    "results/Pyramids/Pyramids/Pyramids-499959.pt"
+                    "results/Pyramids/Pyramids/Pyramids-1499975.pt"
                 ]
             },
             {
-                "steps": 999873,
-                "file_path": "results/Pyramids/Pyramids/Pyramids-999873.onnx",
-                "reward": 1.3980000093579292,
-                "creation_time": 1681649599.2990875,
+                "steps": 1999941,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-1999941.onnx",
+                "reward": 1.5636666384008195,
+                "creation_time": 1681652815.9674253,
                 "auxillary_file_paths": [
-                    "results/Pyramids/Pyramids/Pyramids-999873.pt"
+                    "results/Pyramids/Pyramids/Pyramids-1999941.pt"
                 ]
             },
             {
-                "steps": 1000001,
-                "file_path": "results/Pyramids/Pyramids/Pyramids-1000001.onnx",
-                "reward": 1.3980000093579292,
-                "creation_time": 1681649599.4752176,
+                "steps": 2499893,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-2499893.onnx",
+                "reward": 1.8183333228031795,
+                "creation_time": 1681654120.8597245,
                 "auxillary_file_paths": [
-                    "results/Pyramids/Pyramids/Pyramids-1000001.pt"
+                    "results/Pyramids/Pyramids/Pyramids-2499893.pt"
+                ]
+            },
+            {
+                "steps": 2999891,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-2999891.onnx",
+                "reward": 1.743999981880188,
+                "creation_time": 1681655452.5870383,
+                "auxillary_file_paths": [
+                    "results/Pyramids/Pyramids/Pyramids-2999891.pt"
+                ]
+            },
+            {
+                "steps": 3000019,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-3000019.onnx",
+                "reward": 1.743999981880188,
+                "creation_time": 1681655452.692879,
+                "auxillary_file_paths": [
+                    "results/Pyramids/Pyramids/Pyramids-3000019.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000001,
+            "steps": 3000019,
             "file_path": "results/Pyramids/Pyramids.onnx",
-            "reward": 1.3980000093579292,
-            "creation_time": 1681649599.4752176,
+            "reward": 1.743999981880188,
+            "creation_time": 1681655452.692879,
             "auxillary_file_paths": [
-                "results/Pyramids/Pyramids/Pyramids-1000001.pt"
+                "results/Pyramids/Pyramids/Pyramids-3000019.pt"
             ]
         }
     },