second push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f27986d1cec9f00c3bcdf4a87d4f34d59c4b371cd01b1b77de8fac09101a77b
+size 1420238

Pyramids/Pyramids-1000042.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f27986d1cec9f00c3bcdf4a87d4f34d59c4b371cd01b1b77de8fac09101a77b
+size 1420238

Pyramids/Pyramids-1000042.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8099ee4496b02c552730170e3a2021efa40453e9fe8c8ef38ffc1f7a1fe95f4
+size 8656252

Pyramids/Pyramids-499936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d55789e3c39273e8c8539f08681eca2f736eac8c06d2703a43fbef7d1c302bf
+size 1420238

Pyramids/Pyramids-499936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56523e5c2504ae11134f187df6ac5e62bd464b9da18d3e2ec7c16edd9e6ddbfc
+size 8656173

Pyramids/Pyramids-999938.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f27986d1cec9f00c3bcdf4a87d4f34d59c4b371cd01b1b77de8fac09101a77b
+size 1420238

Pyramids/Pyramids-999938.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1fe44deb91836b7284f17500548f8a47922db0a083ac7ef071f9dff24e81fef
+size 8656173

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e630247e09253ff8134dc90c8329632dd65074adea2b5b86dba39c0b5991f9a4
+size 8655778

Pyramids/events.out.tfevents.1704034895.ce42e5cb1d27.16839.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6a2d2c8e5522366ac444aeff5f3e6fc83714ffca87b95aee07172bbe0186ee5
+size 2091386

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 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, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 100, "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, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "PyramidsTraining", "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

@@ -53,7 +53,7 @@ behaviors:
     even_checkpoints: false
     max_steps: 1000000
     time_horizon: 128
-    summary_freq: 30000
+    summary_freq: 100
     threaded: false
     self_play: null
     behavioral_cloning: null
@@ -79,7 +79,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: PyramidsTraining
   initialize_from: null
   load_model: false
   resume: 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] 55032 [Flags] 2 [Guid] 1090157531 [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] 55122 [Flags] 2 [Guid] 2567394135 [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:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.104 seconds
+- Completed reload, in  0.102 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: 0.868416 ms
+UnloadTime: 0.845295 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]: 3070 frames, [32.0 KB-64.0 KB]: 4757 frames, [64.0 KB-128.0 KB]: 717 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 4995 frames, [32.0 KB-64.0 KB]: 12012 frames, [64.0 KB-128.0 KB]: 1761 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
@@ -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]: 8246 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.5 MB
+  Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 11627
+  Peak main deferred allocation count 12116
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       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]: 8544 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18768 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.5 MB
+      Peak Allocated memory 31.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 8545 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.3 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
@@ -257,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 8544 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18768 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]: 8545 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,13 +272,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 8246 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 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]: 8544 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18768 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
@@ -293,19 +290,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 8545 frames
+      Peak usage frame count: [0-1.0 KB]: 18769 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]: 8545 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18769 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]: 8545 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18769 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.1 KB
@@ -314,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1704034480364,"processId":11272,"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":1704036931790,"processId":16860,"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": 0.8351698517799377,
-            "min": 0.8351698517799377,
-            "max": 1.422520637512207,
-            "count": 15
+            "value": 0.48018190264701843,
+            "min": 0.29809290170669556,
+            "max": 1.609270453453064,
+            "count": 5564
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 24988.28125,
-            "min": 24988.28125,
-            "max": 43153.5859375,
-            "count": 15
+            "value": 15.36582088470459,
+            "min": 4.769486427307129,
+            "max": 3295.785888671875,
+            "count": 5564
         },
         "Pyramids.Step.mean": {
-            "value": 449953.0,
-            "min": 29918.0,
-            "max": 449953.0,
-            "count": 15
+            "value": 999938.0,
+            "min": 128.0,
+            "max": 999938.0,
+            "count": 8013
         },
         "Pyramids.Step.sum": {
-            "value": 449953.0,
-            "min": 29918.0,
-            "max": 449953.0,
-            "count": 15
+            "value": 999938.0,
+            "min": 128.0,
+            "max": 999938.0,
+            "count": 8013
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.20261934399604797,
-            "min": -0.10649552196264267,
-            "max": 0.20261934399604797,
-            "count": 15
+            "value": 0.6090235114097595,
+            "min": -0.18267610669136047,
+            "max": 1.779097080230713,
+            "count": 8013
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 51.46531295776367,
-            "min": -25.55892562866211,
-            "max": 51.46531295776367,
-            "count": 15
+            "value": 0.6090235114097595,
+            "min": -0.18267610669136047,
+            "max": 2.9349684715270996,
+            "count": 8013
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.00882098451256752,
-            "min": -0.00882098451256752,
-            "max": 0.3485966920852661,
-            "count": 15
+            "value": 0.7529672980308533,
+            "min": -2.6109306812286377,
+            "max": 1.5369911193847656,
+            "count": 8013
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -2.240530014038086,
-            "min": -2.240530014038086,
-            "max": 82.61741638183594,
-            "count": 15
+            "value": 0.7529672980308533,
+            "min": -2.8789758682250977,
+            "max": 1.9517099857330322,
+            "count": 8013
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 8013
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 8013
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.0647244514250252,
-            "min": 0.0647244514250252,
-            "max": 0.07242072516485577,
-            "count": 15
+            "value": 0.05967576015973464,
+            "min": 0.05225649633212015,
+            "max": 0.093191156280227,
+            "count": 440
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9061423199503528,
-            "min": 0.49937649448428983,
-            "max": 1.0138901523079809,
-            "count": 15
+            "value": 0.05967576015973464,
+            "min": 0.05225649633212015,
+            "max": 0.093191156280227,
+            "count": 440
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.00904177873538477,
-            "min": 0.0006894308617861576,
-            "max": 0.010915844324329349,
-            "count": 15
+            "value": 0.04791275078120331,
+            "min": 4.096566183708252e-05,
+            "max": 0.07373145610714953,
+            "count": 440
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.1265849022953868,
-            "min": 0.008273170341433891,
-            "max": 0.1265849022953868,
-            "count": 15
+            "value": 0.04791275078120331,
+            "min": 4.096566183708252e-05,
+            "max": 0.07373145610714953,
+            "count": 440
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 0.00016968531486681427,
-            "min": 0.00016968531486681427,
-            "max": 0.00029515063018788575,
-            "count": 15
+            "value": 4.6689984440000056e-07,
+            "min": 4.6689984440000056e-07,
+            "max": 0.0002987712004096,
+            "count": 440
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0023755944081354,
-            "min": 0.0020660544113152,
-            "max": 0.0036323185892271994,
-            "count": 15
+            "value": 4.6689984440000056e-07,
+            "min": 4.6689984440000056e-07,
+            "max": 0.0002987712004096,
+            "count": 440
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.1565617571428572,
-            "min": 0.1565617571428572,
-            "max": 0.19838354285714285,
-            "count": 15
+            "value": 0.10015560000000001,
+            "min": 0.10015560000000001,
+            "max": 0.19959039999999997,
+            "count": 440
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 2.1918646000000006,
-            "min": 1.3886848,
-            "max": 2.6107728000000003,
-            "count": 15
+            "value": 0.10015560000000001,
+            "min": 0.10015560000000001,
+            "max": 0.19959039999999997,
+            "count": 440
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.005660519538571427,
-            "min": 0.005660519538571427,
-            "max": 0.00983851593142857,
-            "count": 15
+            "value": 2.554444000000002e-05,
+            "min": 2.554444000000002e-05,
+            "max": 0.009959080960000002,
+            "count": 440
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.07924727353999998,
-            "min": 0.06886961152,
-            "max": 0.12109620272000002,
-            "count": 15
+            "value": 2.554444000000002e-05,
+            "min": 2.554444000000002e-05,
+            "max": 0.009959080960000002,
+            "count": 440
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.016700027510523796,
-            "min": 0.016700027510523796,
-            "max": 0.4671788215637207,
-            "count": 15
+            "value": 0.009184012189507484,
+            "min": 0.008418445475399494,
+            "max": 0.6469921469688416,
+            "count": 440
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.23380039632320404,
-            "min": 0.23380039632320404,
-            "max": 3.270251750946045,
-            "count": 15
+            "value": 0.009184012189507484,
+            "min": 0.008418445475399494,
+            "max": 0.6469921469688416,
+            "count": 440
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 643.7407407407408,
-            "min": 643.7407407407408,
-            "max": 996.9677419354839,
-            "count": 15
+            "value": 999.0,
+            "min": 11.0,
+            "max": 999.0,
+            "count": 919
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 34762.0,
-            "min": 16845.0,
-            "max": 34762.0,
-            "count": 15
+            "value": 999.0,
+            "min": 11.0,
+            "max": 15984.0,
+            "count": 919
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 0.6153147837354077,
-            "min": -0.9333419857486602,
-            "max": 0.7314092660712641,
-            "count": 15
+            "value": 1.6589999496936798,
+            "min": -1.0000000521540642,
+            "max": 1.9889999628067017,
+            "count": 1166
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 33.22699832171202,
-            "min": -30.387801721692085,
-            "max": 33.22699832171202,
-            "count": 15
+            "value": 1.6589999496936798,
+            "min": -1.0000000521540642,
+            "max": 4.815000057220459,
+            "count": 1166
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 0.6153147837354077,
-            "min": -0.9333419857486602,
-            "max": 0.7314092660712641,
-            "count": 15
+            "value": 1.6589999496936798,
+            "min": -1.0000000521540642,
+            "max": 1.9889999628067017,
+            "count": 1166
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 33.22699832171202,
-            "min": -30.387801721692085,
-            "max": 33.22699832171202,
-            "count": 15
+            "value": 1.6589999496936798,
+            "min": -1.0000000521540642,
+            "max": 4.815000057220459,
+            "count": 1166
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.11265560689261528,
-            "min": 0.11265560689261528,
-            "max": 9.161481977385634,
-            "count": 15
+            "value": 0.03135890141129494,
+            "min": 0.004081433173269033,
+            "max": 6.433250069618225,
+            "count": 1166
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 6.083402772201225,
-            "min": 5.65397814521566,
-            "max": 155.74519361555576,
-            "count": 15
-        },
-        "Pyramids.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 15
-        },
-        "Pyramids.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 15
+            "value": 0.03135890141129494,
+            "min": 0.004081433173269033,
+            "max": 6.433250069618225,
+            "count": 1166
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1704033590",
+        "start_time_seconds": "1704034895",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.1.2+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1704034480"
+        "end_time_seconds": "1704036931"
     },
-    "total": 889.7570780599999,
+    "total": 2036.72524935,
     "count": 1,
-    "self": 0.4873463960002482,
+    "self": 0.49170865599990066,
     "children": {
         "run_training.setup": {
-            "total": 0.045246901999689726,
+            "total": 0.0452882720001071,
             "count": 1,
-            "self": 0.045246901999689726
+            "self": 0.0452882720001071
         },
         "TrainerController.start_learning": {
-            "total": 889.224484762,
+            "total": 2036.188252422,
             "count": 1,
-            "self": 0.5260916380002527,
+            "self": 1.2382923069731078,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.0419645330002822,
+                    "total": 2.0325155730001825,
                     "count": 1,
-                    "self": 2.0419645330002822
+                    "self": 2.0325155730001825
                 },
                 "TrainerController.advance": {
-                    "total": 886.6564274959992,
-                    "count": 28756,
-                    "self": 0.5690567619994908,
+                    "total": 2032.8383778300267,
+                    "count": 63251,
+                    "self": 1.3917753349264785,
                     "children": {
                         "env_step": {
-                            "total": 602.8908191609771,
-                            "count": 28756,
-                            "self": 547.2447025649108,
+                            "total": 1409.8417455580584,
+                            "count": 63251,
+                            "self": 1287.269173110054,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 55.31664915605461,
-                                    "count": 28756,
-                                    "self": 2.026559857025859,
+                                    "total": 121.8179686249614,
+                                    "count": 63251,
+                                    "self": 4.506854764874333,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 53.29008929902875,
-                                            "count": 28482,
-                                            "self": 53.29008929902875
+                                            "total": 117.31111386008706,
+                                            "count": 62562,
+                                            "self": 117.31111386008706
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.3294674400117401,
-                                    "count": 28756,
+                                    "total": 0.7546038230429986,
+                                    "count": 63251,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 887.1152250429996,
-                                            "count": 28756,
+                                            "total": 2031.5094602028466,
+                                            "count": 63251,
                                             "is_parallel": true,
-                                            "self": 388.46404876594397,
+                                            "self": 857.0263799787626,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0016965750000963453,
+                                                            "total": 0.0017279210001106549,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005203969999456604,
+                                                            "self": 0.0005442680007945455,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001176178000150685,
+                                                                    "total": 0.0011836529993161093,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001176178000150685
+                                                                    "self": 0.0011836529993161093
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04734448999988672,
+                                                            "total": 0.04959300300015457,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005783759997939342,
+                                                            "self": 0.0005915800006732752,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004677629999605415,
+                                                                    "total": 0.00044920599975739606,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004677629999605415
+                                                                    "self": 0.00044920599975739606
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04469875899985709,
+                                                                    "total": 0.04688297799975771,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04469875899985709
+                                                                    "self": 0.04688297799975771
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0015995920002751518,
+                                                                    "total": 0.0016692389999661827,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000340226999924198,
+                                                                    "self": 0.0004247789997862128,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0012593650003509538,
+                                                                            "total": 0.00124446000017997,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0012593650003509538
+                                                                            "self": 0.00124446000017997
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 498.6511762770556,
-                                                    "count": 28755,
+                                                    "total": 1174.483080224084,
+                                                    "count": 63250,
                                                     "is_parallel": true,
-                                                    "self": 15.248413436133433,
+                                                    "self": 33.75304913284708,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 10.815642660989852,
-                                                            "count": 28755,
+                                                            "total": 23.193250067060944,
+                                                            "count": 63250,
                                                             "is_parallel": true,
-                                                            "self": 10.815642660989852
+                                                            "self": 23.193250067060944
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 429.67647553191637,
-                                                            "count": 28755,
+                                                            "total": 1022.7778030772665,
+                                                            "count": 63250,
                                                             "is_parallel": true,
-                                                            "self": 429.67647553191637
+                                                            "self": 1022.7778030772665
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 42.91064464801593,
-                                                            "count": 28755,
+                                                            "total": 94.75897794690945,
+                                                            "count": 63250,
                                                             "is_parallel": true,
-                                                            "self": 8.305702126982396,
+                                                            "self": 18.507106582729193,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 34.604942521033536,
-                                                                    "count": 230040,
+                                                                    "total": 76.25187136418026,
+                                                                    "count": 506000,
                                                                     "is_parallel": true,
-                                                                    "self": 34.604942521033536
+                                                                    "self": 76.25187136418026
                                                                 }
                                                             }
                                                         }
@@ -343,24 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 283.1965515730226,
-                            "count": 28756,
-                            "self": 0.9902349150270311,
+                            "total": 621.6048569370419,
+                            "count": 63251,
+                            "self": 2.257398964080039,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 53.70423475499774,
-                                    "count": 28756,
-                                    "self": 53.70423475499774
+                                    "total": 134.2001486679692,
+                                    "count": 63251,
+                                    "self": 134.01751130796947,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.18263735999971686,
+                                            "count": 2,
+                                            "self": 0.18263735999971686
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 228.50208190299782,
-                                    "count": 198,
-                                    "self": 135.39506550102533,
+                                    "total": 485.14730930499263,
+                                    "count": 440,
+                                    "self": 285.9545768540165,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 93.10701640197249,
-                                            "count": 10338,
-                                            "self": 93.10701640197249
+                                            "total": 199.1927324509761,
+                                            "count": 22806,
+                                            "self": 199.1927324509761
                                         }
                                     }
                                 }
@@ -369,9 +376,21 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0950002433673944e-06,
+                    "total": 8.560000424040481e-07,
+                    "count": 1,
+                    "self": 8.560000424040481e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.07906585599994287,
                     "count": 1,
-                    "self": 1.0950002433673944e-06
+                    "self": 0.001403623999976844,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.07766223199996602,
+                            "count": 1,
+                            "self": 0.07766223199996602
+                        }
+                    }
                 }
             }
         }

run_logs/training_status.json

@@ -1,4 +1,44 @@
 {
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499936,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-499936.onnx",
+                "reward": -1.0000000521540642,
+                "creation_time": 1704035881.4901052,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-499936.pt"
+                ]
+            },
+            {
+                "steps": 999938,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-999938.onnx",
+                "reward": 1.6589999496936798,
+                "creation_time": 1704036931.2551322,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-999938.pt"
+                ]
+            },
+            {
+                "steps": 1000042,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1000042.onnx",
+                "reward": 0.32989995181560516,
+                "creation_time": 1704036931.3442314,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-1000042.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000042,
+            "file_path": "results/PyramidsTraining/Pyramids.onnx",
+            "reward": 0.32989995181560516,
+            "creation_time": 1704036931.3442314,
+            "auxillary_file_paths": [
+                "results/PyramidsTraining/Pyramids/Pyramids-1000042.pt"
+            ]
+        }
+    },
     "metadata": {
         "stats_format_version": "0.3.0",
         "mlagents_version": "1.1.0.dev0",