Second Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a038497b95e5ea273310005ab07c7469436f1cc7b512bacff3212d5361229a
+oid sha256:49083958f8bc369e0fe8b425c2667f40fef77f8f999170eca249f85f7b81e807
 size 1420238

Pyramids/Pyramids-1499969.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:212aa505fd1fea1b373cc783f6f753164904f70cd103aec32f838b452c9b02d0
+size 1420238

Pyramids/Pyramids-1499969.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04092b59ef4c95effc863e9f5206443923690c241f1f1591ab75a452539801f4
+size 8809219

Pyramids/Pyramids-1999960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee677badbe8f38d0a4253b23d04d93d991c2b7f61e729b1a2e3068203adb3b1e
+size 1420238

Pyramids/Pyramids-1999960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c5eab93aabeb2c4ada8aeafe06b72be072d89110d725f39f7983c2489f014e
+size 8809219

Pyramids/Pyramids-2499977.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f37a72a8f8cbc92d362783a623eb63b750a731a34a943cda1bc1f32c14312e
+size 1420238

Pyramids/Pyramids-2499977.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b1bdcf64c2e6a49fdcc2f3b01f9b7470420e3610eace6223d6b122c71c28bf
+size 8809219

Pyramids/Pyramids-2999873.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49083958f8bc369e0fe8b425c2667f40fef77f8f999170eca249f85f7b81e807
+size 1420238

Pyramids/Pyramids-2999873.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec0158f1b0d05b0e868bb339e901de5beb55efb4090b3f0ae14380a602cf2846
+size 8809219

Pyramids/Pyramids-3000001.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49083958f8bc369e0fe8b425c2667f40fef77f8f999170eca249f85f7b81e807
+size 1420238

Pyramids/Pyramids-3000001.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3099c0e1dd23e6acf501c537d95c10039704c9eee1ef2a20fb548425d3a28ce0
+size 8809219

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2692179afd93b5f7a4e784f7b1471d4a34c6bf728790d6be7558a53d873e3a2
-size 8942389
+oid sha256:9c25e67a6cacdfa1bc3fcdeabaf14673e36df527b70cdf46634f1fd2fa7cdf04
+size 8808757

Pyramids/events.out.tfevents.1756817588.hungchan-Precision-7560.63834.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cab5c8878b33a51e822ba9b87e932528bfef970381fb2d709d206967c220c413
+size 1017325

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 5120, "learning_rate": 0.0001, "beta": 0.015, "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": 0.995, "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": 0.1, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "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, "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": 512, "buffer_size": 10240, "learning_rate": 0.0001, "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": 0.995, "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": 0.1, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "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, "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 Run 2", "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

@@ -4,9 +4,9 @@ behaviors:
     trainer_type: ppo
     hyperparameters:
       batch_size: 512
-      buffer_size: 5120
+      buffer_size: 10240
       learning_rate: 0.0001
-      beta: 0.015
+      beta: 0.01
       epsilon: 0.2
       lambd: 0.95
       num_epoch: 3
@@ -41,12 +41,12 @@ behaviors:
         network_settings:
           normalize: false
           hidden_units: 128
-          num_layers: 3
+          num_layers: 2
           vis_encode_type: simple
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
-        learning_rate: 0.0003
+        learning_rate: 0.0001
         encoding_size: null
     init_path: null
     keep_checkpoints: 5
@@ -79,7 +79,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: Pyramids Training Run 2
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/media/hungchan/Storage/Works/xai/X AI/Code/Hugging Face RL/5. Unity ML-agent/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/media/hungchan/Storage/Works/xai/X AI/Code/Hugging Face RL/5. Unity ML-agent/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 192.168.1.10
-Multi-casting "[IP] 192.168.1.10 [Port] 55360 [Flags] 2 [Guid] 1862415126 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.1.10) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 192.168.1.10 [Port] 55455 [Flags] 2 [Guid] 1548498901 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.1.10) [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: /home/hungchan/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /home/hungchan/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /media/hungchan/Storage/Works/xai/X AI/Code/Hugging Face RL/5. Unity ML-agent/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -48,7 +45,7 @@ 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: 0.531279 ms
+UnloadTime: 0.685386 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 8 worker threads for Enlighten.
@@ -56,7 +53,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 15753 frames, [32.0 KB-64.0 KB]: 30116 frames, [64.0 KB-128.0 KB]: 10403 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 15130 frames, [32.0 KB-64.0 KB]: 31368 frames, [64.0 KB-128.0 KB]: 9770 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
@@ -121,11 +118,6 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
-      Initial Block Size 32.0 KB
-      Current Block Size 32.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -139,7 +131,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 1]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 10]
       Initial Block Size 256.0 KB
@@ -156,6 +148,11 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 320.0 KB
       Peak Allocated Bytes 251.6 KB
       Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_AUDIO_FMOD PulseAudio Mixer]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
@@ -194,7 +191,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 2]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
@@ -216,24 +213,19 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 6]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
     [ALLOC_TEMP_Job.Worker 5]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
-      Initial Block Size 32.0 KB
-      Current Block Size 32.0 KB
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_EnlightenWorker] x 8
@@ -246,6 +238,11 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Job.Worker 7]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
@@ -257,28 +254,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 159 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55974 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55970 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12580
+  Peak main deferred allocation count 11181
     [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]: 56271 frames, [32.0 MB-64.0 MB]: 1 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 56267 frames, [32.0 MB-64.0 MB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 32.3 MB
+      Peak Allocated memory 32.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 56273 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56269 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 27.3 MB
+      Peak Allocated memory 26.2 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -307,13 +304,13 @@ 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]: 56272 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 56268 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]: 56273 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 56269 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -325,13 +322,13 @@ 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]: 55974 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55970 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]: 56272 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 56268 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
@@ -343,19 +340,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 56273 frames
+      Peak usage frame count: [0-1.0 KB]: 56269 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]: 56273 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 56269 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: [32.0 KB-64.0 KB]: 56273 frames
+  Peak usage frame count: [32.0 KB-64.0 KB]: 56269 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 38.0 KB
@@ -364,4 +361,4 @@ 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":1756811134930,"processId":12700,"allocatedMemory":2044915,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":73418},{"Thread":34852},{"Manager":18447},{"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":3664},{"DynamicArray":30868},{"HashMap":7680},{"Utility":7072},{"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":1756821270704,"processId":63884,"allocatedMemory":2044915,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":73418},{"Thread":34852},{"Manager":18447},{"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":3664},{"DynamicArray":30868},{"HashMap":7680},{"Utility":7072},{"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

@@ -2,171 +2,171 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.3648880124092102,
-            "min": 0.3586031198501587,
-            "max": 1.5152931213378906,
+            "value": 0.31941959261894226,
+            "min": 0.31941959261894226,
+            "max": 1.5913751125335693,
             "count": 100
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 10993.345703125,
-            "min": 10647.3603515625,
-            "max": 45967.93359375,
+            "value": 9597.919921875,
+            "min": 9597.919921875,
+            "max": 48275.95703125,
             "count": 100
         },
         "Pyramids.Step.mean": {
-            "value": 2999889.0,
+            "value": 2999873.0,
             "min": 29952.0,
-            "max": 2999889.0,
+            "max": 2999873.0,
             "count": 100
         },
         "Pyramids.Step.sum": {
-            "value": 2999889.0,
+            "value": 2999873.0,
             "min": 29952.0,
-            "max": 2999889.0,
+            "max": 2999873.0,
             "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.4423373341560364,
-            "min": -0.15380437672138214,
-            "max": 0.9697663187980652,
+            "value": 0.746780514717102,
+            "min": -0.1449412703514099,
+            "max": 0.8288553953170776,
             "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 114.12303161621094,
-            "min": -37.066856384277344,
-            "max": 275.41363525390625,
+            "value": 203.87107849121094,
+            "min": -34.93084716796875,
+            "max": 233.7372283935547,
             "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.07140153646469116,
-            "min": -0.961536705493927,
-            "max": 5.297674655914307,
+            "value": 0.9310639500617981,
+            "min": 0.9151319265365601,
+            "max": 26.376020431518555,
             "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -18.42159652709961,
-            "min": -265.3841247558594,
-            "max": 1271.44189453125,
+            "value": 254.1804656982422,
+            "min": 252.17361450195312,
+            "max": 6356.62109375,
             "count": 100
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.02993082449150582,
-            "min": 0.02849066569987271,
-            "max": 0.03923334629243155,
+            "value": 0.03764318283388598,
+            "min": 0.030007568025030195,
+            "max": 0.04330179998274344,
             "count": 100
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.17958494694903493,
-            "min": 0.14626130897862216,
-            "max": 0.23087790133431554,
+            "value": 0.11292954850165793,
+            "min": 0.06378415991396955,
+            "max": 0.12503808459588506,
             "count": 100
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.03069851579558518,
-            "min": 0.002553138680781962,
-            "max": 3.253386940026299,
+            "value": 0.015089578854127062,
+            "min": 0.011777677055862216,
+            "max": 50.34082246057078,
             "count": 100
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.1841910947735111,
-            "min": 0.015318832084691772,
-            "max": 13.013547760105196,
+            "value": 0.04526873656238119,
+            "min": 0.025758922534684342,
+            "max": 100.68164492114155,
             "count": 100
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 5.28643915900003e-07,
-            "min": 5.28643915900003e-07,
-            "max": 9.94944005056e-05,
+            "value": 4.844772934000003e-07,
+            "min": 4.844772934000003e-07,
+            "max": 9.939200060800002e-05,
             "count": 100
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 3.171863495400018e-06,
-            "min": 3.171863495400018e-06,
-            "max": 0.0005790079209921001,
+            "value": 1.4534318802000007e-06,
+            "min": 1.4534318802000007e-06,
+            "max": 0.00029531847134820003,
             "count": 100
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10052854444444446,
-            "min": 0.10052854444444446,
-            "max": 0.19949440000000002,
+            "value": 0.10048437777777779,
+            "min": 0.10048437777777779,
+            "max": 0.19939199999999999,
             "count": 100
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 0.6031712666666668,
-            "min": 0.5073915,
-            "max": 1.1790079000000002,
+            "value": 0.30145313333333335,
+            "min": 0.21301233333333333,
+            "max": 0.5953184666666668,
             "count": 100
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 8.922881222222263e-05,
-            "min": 8.922881222222263e-05,
-            "max": 0.01492421056,
+            "value": 5.8389340000000017e-05,
+            "min": 5.8389340000000017e-05,
+            "max": 0.009939260800000002,
             "count": 100
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0005353728733333358,
-            "min": 0.0005353728733333358,
-            "max": 0.08685328420999999,
+            "value": 0.00017516802000000004,
+            "min": 0.00017516802000000004,
+            "max": 0.029532314820000002,
             "count": 100
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.020344262942671776,
-            "min": 0.019488167017698288,
-            "max": 0.8116133213043213,
+            "value": 0.10602808743715286,
+            "min": 0.10435324162244797,
+            "max": 5.4608564376831055,
             "count": 100
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.12206558138132095,
-            "min": 0.09929914772510529,
-            "max": 3.246453285217285,
+            "value": 0.3180842697620392,
+            "min": 0.20994243025779724,
+            "max": 10.921712875366211,
             "count": 100
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 515.0714285714286,
-            "min": 282.6504854368932,
+            "value": 364.8,
+            "min": 340.8255813953488,
             "max": 999.0,
             "count": 100
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 28844.0,
+            "value": 27360.0,
             "min": 15984.0,
-            "max": 32957.0,
+            "max": 33116.0,
             "count": 100
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.0562321172494973,
+            "value": 1.5551786492268245,
             "min": -1.0000000521540642,
-            "max": 1.7068762734685976,
+            "max": 1.626434069465507,
             "count": 100
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 59.14899856597185,
-            "min": -32.000001668930054,
-            "max": 174.88659876585007,
+            "value": 116.63839869201183,
+            "min": -31.99600164592266,
+            "max": 147.78939798474312,
             "count": 100
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.0562321172494973,
+            "value": 1.5551786492268245,
             "min": -1.0000000521540642,
-            "max": 1.7068762734685976,
+            "max": 1.626434069465507,
             "count": 100
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 59.14899856597185,
-            "min": -32.000001668930054,
-            "max": 174.88659876585007,
+            "value": 116.63839869201183,
+            "min": -31.99600164592266,
+            "max": 147.78939798474312,
             "count": 100
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 1.0782365690683946,
-            "min": 0.6000466791741116,
-            "max": 186.66918002068996,
+            "value": 3.9185459551836055,
+            "min": 3.687487304524478,
+            "max": 917.0562484264374,
             "count": 100
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 60.3812478678301,
-            "min": 57.350965306162834,
-            "max": 2986.7068803310394,
+            "value": 293.8909466387704,
+            "min": 292.1203705649823,
+            "max": 14672.899974822998,
             "count": 100
         },
         "Pyramids.IsTraining.mean": {
@@ -184,67 +184,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1756807880",
+        "start_time_seconds": "1756817588",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/home/hungchan/miniconda3/envs/rl_31012/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/home/hungchan/miniconda3/envs/rl_31012/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training Run 2 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1756811134"
+        "end_time_seconds": "1756821270"
     },
-    "total": 3254.906885005,
+    "total": 3682.686553206,
     "count": 1,
-    "self": 0.2768450399998983,
+    "self": 0.3711183870000241,
     "children": {
         "run_training.setup": {
-            "total": 0.0508246000000554,
+            "total": 0.015643329999875277,
             "count": 1,
-            "self": 0.0508246000000554
+            "self": 0.015643329999875277
         },
         "TrainerController.start_learning": {
-            "total": 3254.579215365,
+            "total": 3682.299791489,
             "count": 1,
-            "self": 3.9781296309993195,
+            "self": 4.471573963244737,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.6173410069999363,
+                    "total": 1.4596728899996378,
                     "count": 1,
-                    "self": 1.6173410069999363
+                    "self": 1.4596728899996378
                 },
                 "TrainerController.advance": {
-                    "total": 3248.9333752689995,
-                    "count": 192208,
-                    "self": 3.8575478021493836,
+                    "total": 3676.2634758217555,
+                    "count": 191819,
+                    "self": 4.349057315184837,
                     "children": {
                         "env_step": {
-                            "total": 2403.0913357258564,
-                            "count": 192208,
-                            "self": 2043.4582030849242,
+                            "total": 2625.6239074529876,
+                            "count": 191819,
+                            "self": 2112.8629158190943,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 356.9428961030411,
-                                    "count": 192208,
-                                    "self": 10.942023073978817,
+                                    "total": 509.92004004172304,
+                                    "count": 191819,
+                                    "self": 12.48315074475795,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 346.0008730290623,
-                                            "count": 187576,
-                                            "self": 346.0008730290623
+                                            "total": 497.4368892969651,
+                                            "count": 187562,
+                                            "self": 497.4368892969651
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 2.6902365378909963,
-                                    "count": 192208,
+                                    "total": 2.8409515921703132,
+                                    "count": 191819,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 3249.4381485699073,
-                                            "count": 192208,
+                                            "total": 3676.8532693950747,
+                                            "count": 191819,
                                             "is_parallel": true,
-                                            "self": 1447.6441811618483,
+                                            "self": 1823.0812916923696,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0015645739999854413,
+                                                            "total": 0.0010134390013263328,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006215849999762213,
+                                                            "self": 0.00029463299870258197,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.00094298900000922,
+                                                                    "total": 0.0007188060026237508,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00094298900000922
+                                                                    "self": 0.0007188060026237508
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.022063921000039954,
+                                                            "total": 0.022171808001075988,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0003220639999881314,
+                                                            "self": 0.0002565689992479747,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00025572000004103757,
+                                                                    "total": 0.00017987100000027567,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00025572000004103757
+                                                                    "self": 0.00017987100000027567
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.020777554000005694,
+                                                                    "total": 0.02116701700106205,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.020777554000005694
+                                                                    "self": 0.02116701700106205
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0007085830000050919,
+                                                                    "total": 0.0005683510007656878,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00016922600025282009,
+                                                                    "self": 0.00014758399993297644,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0005393569997522718,
+                                                                            "total": 0.00042076700083271135,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0005393569997522718
+                                                                            "self": 0.00042076700083271135
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1801.793967408059,
-                                                    "count": 192207,
+                                                    "total": 1853.771977702705,
+                                                    "count": 191818,
                                                     "is_parallel": true,
-                                                    "self": 48.72282670608752,
+                                                    "self": 49.113975984328135,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 34.8379522510445,
-                                                            "count": 192207,
+                                                            "total": 36.795314528650124,
+                                                            "count": 191818,
                                                             "is_parallel": true,
-                                                            "self": 34.8379522510445
+                                                            "self": 36.795314528650124
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1585.4346769339122,
-                                                            "count": 192207,
+                                                            "total": 1633.0751300659904,
+                                                            "count": 191818,
                                                             "is_parallel": true,
-                                                            "self": 1585.4346769339122
+                                                            "self": 1633.0751300659904
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 132.79851151701473,
-                                                            "count": 192207,
+                                                            "total": 134.7875571237364,
+                                                            "count": 191818,
                                                             "is_parallel": true,
-                                                            "self": 30.497360784974717,
+                                                            "self": 30.88800354094201,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 102.30115073204001,
-                                                                    "count": 1537656,
+                                                                    "total": 103.8995535827944,
+                                                                    "count": 1534544,
                                                                     "is_parallel": true,
-                                                                    "self": 102.30115073204001
+                                                                    "self": 103.8995535827944
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 841.9844917409937,
-                            "count": 192208,
-                            "self": 7.850889706003613,
+                            "total": 1046.290511053583,
+                            "count": 191819,
+                            "self": 8.3830967354952,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 243.33867124098867,
-                                    "count": 192208,
-                                    "self": 242.87500665398795,
+                                    "total": 330.46261656308525,
+                                    "count": 191819,
+                                    "self": 329.9796428390855,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.46366458700072144,
+                                            "total": 0.48297372399974847,
                                             "count": 6,
-                                            "self": 0.46366458700072144
+                                            "self": 0.48297372399974847
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 590.7949307940014,
-                                    "count": 571,
-                                    "self": 449.5698461020147,
+                                    "total": 707.4447977550026,
+                                    "count": 289,
+                                    "self": 501.9307063850556,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 141.2250846919867,
-                                            "count": 17277,
-                                            "self": 141.2250846919867
+                                            "total": 205.51409136994698,
+                                            "count": 17421,
+                                            "self": 205.51409136994698
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.10000380827114e-07,
+                    "total": 8.53000528877601e-07,
                     "count": 1,
-                    "self": 9.10000380827114e-07
+                    "self": 8.53000528877601e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.050368548000733426,
+                    "total": 0.1050679609998042,
                     "count": 1,
-                    "self": 0.0009564040001350804,
+                    "self": 0.001174913000795641,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.049412144000598346,
+                            "total": 0.10389304799900856,
                             "count": 1,
-                            "self": 0.049412144000598346
+                            "self": 0.10389304799900856
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 1499963,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499963.onnx",
-                "reward": 1.7101666182279587,
-                "creation_time": 1756809478.994942,
+                "steps": 1499969,
+                "file_path": "results/Pyramids Training Run 2/Pyramids/Pyramids-1499969.onnx",
+                "reward": 1.3157110959291458,
+                "creation_time": 1756819100.5176795,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1499963.pt"
+                    "results/Pyramids Training Run 2/Pyramids/Pyramids-1499969.pt"
                 ]
             },
             {
-                "steps": 1999875,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999875.onnx",
-                "reward": 1.6790833187599976,
-                "creation_time": 1756810023.7486002,
+                "steps": 1999960,
+                "file_path": "results/Pyramids Training Run 2/Pyramids/Pyramids-1999960.onnx",
+                "reward": 1.3559411527479397,
+                "creation_time": 1756819669.423975,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1999875.pt"
+                    "results/Pyramids Training Run 2/Pyramids/Pyramids-1999960.pt"
                 ]
             },
             {
-                "steps": 2499942,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499942.onnx",
-                "reward": 1.6999999582767487,
-                "creation_time": 1756810576.229811,
+                "steps": 2499977,
+                "file_path": "results/Pyramids Training Run 2/Pyramids/Pyramids-2499977.onnx",
+                "reward": 1.7074333225687346,
+                "creation_time": 1756820462.8359368,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-2499942.pt"
+                    "results/Pyramids Training Run 2/Pyramids/Pyramids-2499977.pt"
                 ]
             },
             {
-                "steps": 2999889,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999889.onnx",
-                "reward": -0.999800056219101,
-                "creation_time": 1756811134.6330178,
+                "steps": 2999873,
+                "file_path": "results/Pyramids Training Run 2/Pyramids/Pyramids-2999873.onnx",
+                "reward": 1.3535399660468102,
+                "creation_time": 1756821270.2678318,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-2999889.pt"
+                    "results/Pyramids Training Run 2/Pyramids/Pyramids-2999873.pt"
                 ]
             },
             {
-                "steps": 3000017,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000017.onnx",
-                "reward": -0.999800056219101,
-                "creation_time": 1756811134.6921918,
+                "steps": 3000001,
+                "file_path": "results/Pyramids Training Run 2/Pyramids/Pyramids-3000001.onnx",
+                "reward": 1.3535399660468102,
+                "creation_time": 1756821270.390212,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-3000017.pt"
+                    "results/Pyramids Training Run 2/Pyramids/Pyramids-3000001.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 3000017,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": -0.999800056219101,
-            "creation_time": 1756811134.6921918,
+            "steps": 3000001,
+            "file_path": "results/Pyramids Training Run 2/Pyramids.onnx",
+            "reward": 1.3535399660468102,
+            "creation_time": 1756821270.390212,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-3000017.pt"
+                "results/Pyramids Training Run 2/Pyramids/Pyramids-3000001.pt"
             ]
         }
     },