Second Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4f00f2268ca43d038a5b1c5a17d3a440e613565a01a4820b5e49c26dc268b2e
+oid sha256:348118097b397f0686223be14f667e18ac57a0d2cba996b8068f8c52784f83c0
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1c4d1102f2aa225579cb38a7082622183c3fa04399b6b3c5ba3f5f806cc546b
+oid sha256:d27307a31ab53d8db4fdcb4c87d6fd4fd40eb4867562eb51e4c1334387adf3b3
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b7987fcf12fbf72905f2121aa5893fcfcbf424ec2ed8e20e640ef6c4f09d3dc
+oid sha256:6c5ec5bfd910eb1d1844498d76c9ef37c97a44fb51e4ad081f1ecfcb0172113e
 size 3850564

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4f00f2268ca43d038a5b1c5a17d3a440e613565a01a4820b5e49c26dc268b2e
+oid sha256:348118097b397f0686223be14f667e18ac57a0d2cba996b8068f8c52784f83c0
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871eb4657b419c66154f7fa383111aec1d930fdaa600b30387eba7da0e494d0e
+oid sha256:587fcf7273922e2d132c3c18e167d09d0f897d6712ded43aeb6df7b8d8dd225d
 size 3850564

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348118097b397f0686223be14f667e18ac57a0d2cba996b8068f8c52784f83c0
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66ef332d5ecd3826ece87167d1147aa6d25cf126f7851c19545b979bc7f7aea8
+size 3850564

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca505b7d047f600923af93fc235e6b562824aecb43eee753afb0eb129fb3fa8
+size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b6900c7cc903d637aed125a3a8d8fc6d9cbf62ecb3d662bd044684659f95d3f
+size 3850487

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05799e402c0633f241da2067a533d4345796cae731a2b640e17fb4330d8b141
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cfac85c6e9163548e3b866c3e05a335fa855711df1ba98c1bb766b4f9fd71f8
+size 3850487

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f702dee9c1d5ed40384c364e4a67bc6c2a450d6df7a84e33f5a3615246488e3e
+oid sha256:8eb350d7fb4ec20139ff83c77dc67d253943fb75ecfd2080149a1307d4214441
 size 3849717

SnowballTarget/events.out.tfevents.1756743646.hungchan-Precision-7560.12661.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c899a249dba53b8bbe07330db8d2506a64e28cd60af7825417f0e678c1bec38
+size 44157

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "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}}}, "init_path": null, "keep_checkpoints": 100, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 128, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "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": "SnowballTarget1", "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": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 1024, "buffer_size": 10240, "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": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "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}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "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": "SnowballTarget1", "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

@@ -3,10 +3,10 @@ behaviors:
   SnowballTarget:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 128
-      buffer_size: 2048
+      batch_size: 1024
+      buffer_size: 10240
       learning_rate: 0.0003
-      beta: 0.005
+      beta: 0.01
       epsilon: 0.2
       lambd: 0.95
       num_epoch: 3
@@ -36,10 +36,10 @@ behaviors:
           goal_conditioning_type: hyper
           deterministic: false
     init_path: null
-    keep_checkpoints: 100
+    keep_checkpoints: 10
     even_checkpoints: false
     max_steps: 200000
-    time_horizon: 128
+    time_horizon: 64
     summary_freq: 10000
     threaded: false
     self_play: null

run_logs/Player-0.log

@@ -1,40 +1,20 @@
-Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
-Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Mono path[0] = '/media/hungchan/Storage/Works/xai/X AI/Code/Hugging Face RL/5. Unity ML-agent/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/media/hungchan/Storage/Works/xai/X AI/Code/Hugging Face RL/5. Unity ML-agent/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
+PlayerPrefs - Creating folder: /home/hungchan/.config/unity3d/Hugging Face
+PlayerPrefs - Creating folder: /home/hungchan/.config/unity3d/Hugging Face/SnowballTarget
 Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
-[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+[Subsystems] Discovering subsystems at path /media/hungchan/Storage/Works/xai/X AI/Code/Hugging Face RL/5. Unity ML-agent/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
     Version:  NULL 1.0 [1.0]
     Renderer: Null Device
     Vendor:   Unity Technologies
-ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
-ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
-ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
-ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
-ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
-FMOD failed to initialize the output device.: "Error initializing output device. " (60)
-Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
-ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
-ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
-ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
-ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
-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  0.198 seconds
+- Completed reload, in  0.053 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)
@@ -45,15 +25,15 @@ 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: 0.712103 ms
+UnloadTime: 0.514438 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.
+Setting up 8 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5368 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 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
@@ -61,22 +41,22 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 198 B
+      Peak Allocated Bytes 336 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
       Current Block Size 304.0 KB
-      Peak Allocated Bytes 228.9 KB
+      Peak Allocated Bytes 229.0 KB
       Overflow Count 4
     [ALLOC_TEMP_Background Job.Worker 8]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
-      Initial Block Size 32.0 KB
-      Current Block Size 32.0 KB
-      Peak Allocated Bytes 0 B
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
@@ -88,6 +68,16 @@ Memory Statistics:
       Current Block Size 32.0 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 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -98,12 +88,32 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 13]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_EnlightenWorker]
+    [ALLOC_TEMP_EnlightenWorker] x 8
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
@@ -128,7 +138,7 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 15
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
@@ -138,26 +148,66 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 13]
       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 11]
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
       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 3]
+    [ALLOC_TEMP_Background Job.Worker 11]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 4]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -169,22 +219,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 44
+  Peak main deferred allocation count 37
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 5460 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 6.6 MB
+      Peak Allocated memory 6.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.9 MB
+      Peak Allocated memory 17.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -213,13 +263,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5200 frames, [64.0 KB-128.0 KB]: 260 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4045 frames, [64.0 KB-128.0 KB]: 1413 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 68.2 KB
+      Peak Allocated memory 66.8 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5460 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +281,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5458 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5459 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -249,13 +299,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5460 frames
+      Peak usage frame count: [0-1.0 KB]: 5458 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]: 5460 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,15 +2,15 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.8220321536064148,
-            "min": 0.8220321536064148,
-            "max": 2.847947120666504,
+            "value": 2.008164882659912,
+            "min": 2.008164882659912,
+            "max": 2.890336751937866,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 7884.9326171875,
-            "min": 7884.9326171875,
-            "max": 30091.671875,
+            "value": 19085.599609375,
+            "min": 19085.599609375,
+            "max": 29620.40234375,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 13.000184059143066,
-            "min": 0.2609281539916992,
-            "max": 13.181014060974121,
+            "value": 5.566380023956299,
+            "min": 0.042696863412857056,
+            "max": 5.566380023956299,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 1313.0185546875,
-            "min": 25.31003189086914,
-            "max": 1343.503173828125,
+            "value": 1085.444091796875,
+            "min": 8.283191680908203,
+            "max": 1085.444091796875,
             "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -44,171 +44,171 @@
             "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 10945.0,
+            "value": 8756.0,
             "min": 8756.0,
             "max": 10945.0,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 25.884615384615383,
-            "min": 3.227272727272727,
-            "max": 26.09090909090909,
+            "value": 14.522727272727273,
+            "min": 2.6136363636363638,
+            "max": 14.927272727272728,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1346.0,
-            "min": 142.0,
-            "max": 1435.0,
+            "value": 639.0,
+            "min": 115.0,
+            "max": 821.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 25.884615384615383,
-            "min": 3.227272727272727,
-            "max": 26.09090909090909,
+            "value": 14.522727272727273,
+            "min": 2.6136363636363638,
+            "max": 14.927272727272728,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1346.0,
-            "min": 142.0,
-            "max": 1435.0,
+            "value": 639.0,
+            "min": 115.0,
+            "max": 821.0,
             "count": 20
         },
-        "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.0710841607295722,
-            "min": 0.062497492628480186,
-            "max": 0.07584136624263563,
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
             "count": 20
         },
-        "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2843366429182888,
-            "min": 0.25328339660969573,
-            "max": 0.37920683121317816,
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
             "count": 20
         },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.020801379935195048,
+            "min": 0.01685354337096214,
+            "max": 0.029999618922981124,
+            "count": 19
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.020801379935195048,
+            "min": 0.01685354337096214,
+            "max": 0.029999618922981124,
+            "count": 19
+        },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.21017864653292823,
-            "min": 0.11963415763103494,
-            "max": 0.3085648624336018,
-            "count": 20
+            "value": 0.355442476272583,
+            "min": 0.09278392195701599,
+            "max": 0.3592230121294657,
+            "count": 19
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.8407145861317129,
-            "min": 0.47853663052413975,
-            "max": 1.5428243121680092,
-            "count": 20
+            "value": 0.355442476272583,
+            "min": 0.09278392195701599,
+            "max": 0.3592230121294657,
+            "count": 19
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 7.950097350000008e-06,
-            "min": 7.950097350000008e-06,
-            "max": 0.00029175000274999995,
-            "count": 20
+            "value": 1.9440993520000114e-06,
+            "min": 1.9440993520000114e-06,
+            "max": 0.00028363200545599993,
+            "count": 19
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.180038940000003e-05,
-            "min": 3.180038940000003e-05,
-            "max": 0.0013845000385,
-            "count": 20
+            "value": 1.9440993520000114e-06,
+            "min": 1.9440993520000114e-06,
+            "max": 0.00028363200545599993,
+            "count": 19
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10265,
-            "min": 0.10265,
-            "max": 0.19725000000000004,
-            "count": 20
+            "value": 0.10064800000000003,
+            "min": 0.10064800000000003,
+            "max": 0.19454399999999994,
+            "count": 19
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.4106,
-            "min": 0.4106,
-            "max": 0.9615,
-            "count": 20
+            "value": 0.10064800000000003,
+            "min": 0.10064800000000003,
+            "max": 0.19454399999999994,
+            "count": 19
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.00014223500000000013,
-            "min": 0.00014223500000000013,
-            "max": 0.004862775,
-            "count": 20
+            "value": 7.473520000000039e-05,
+            "min": 7.473520000000039e-05,
+            "max": 0.009454945599999997,
+            "count": 19
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005689400000000005,
-            "min": 0.0005689400000000005,
-            "max": 0.023078849999999998,
-            "count": 20
-        },
-        "SnowballTarget.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 20
-        },
-        "SnowballTarget.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 20
+            "value": 7.473520000000039e-05,
+            "min": 7.473520000000039e-05,
+            "max": 0.009454945599999997,
+            "count": 19
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1756517271",
-        "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "start_time_seconds": "1756743646",
+        "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 ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1756517669"
+        "end_time_seconds": "1756743833"
     },
-    "total": 397.99137067499987,
+    "total": 186.97781900200016,
     "count": 1,
-    "self": 0.43407526399983,
+    "self": 0.21862168200004817,
     "children": {
         "run_training.setup": {
-            "total": 0.02226717999997163,
+            "total": 0.013576254000099652,
             "count": 1,
-            "self": 0.02226717999997163
+            "self": 0.013576254000099652
         },
         "TrainerController.start_learning": {
-            "total": 397.53502823100007,
+            "total": 186.745621066,
             "count": 1,
-            "self": 0.32291470100835795,
+            "self": 0.22402318901185936,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.1486366469998757,
+                    "total": 1.2709940259999257,
                     "count": 1,
-                    "self": 3.1486366469998757
+                    "self": 1.2709940259999257
                 },
                 "TrainerController.advance": {
-                    "total": 393.9864899499919,
-                    "count": 18200,
-                    "self": 0.3462788280062341,
+                    "total": 185.17632726798843,
+                    "count": 18192,
+                    "self": 0.21790039998245447,
                     "children": {
                         "env_step": {
-                            "total": 283.82654264898474,
-                            "count": 18200,
-                            "self": 217.68852903493098,
+                            "total": 142.81059462600797,
+                            "count": 18192,
+                            "self": 108.78446163200192,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 65.93661272603094,
-                                    "count": 18200,
-                                    "self": 1.2259311820266703,
+                                    "total": 33.88783405701088,
+                                    "count": 18192,
+                                    "self": 0.6471468669826663,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 64.71068154400427,
-                                            "count": 18200,
-                                            "self": 64.71068154400427
+                                            "total": 33.24068719002821,
+                                            "count": 18192,
+                                            "self": 33.24068719002821
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.20140088802281753,
-                                    "count": 18200,
+                                    "total": 0.13829893699517015,
+                                    "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 396.3193719890139,
-                                            "count": 18200,
+                                            "total": 186.2964024690143,
+                                            "count": 18192,
                                             "is_parallel": true,
-                                            "self": 205.07016125201312,
+                                            "self": 91.90503982399446,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005182115000025078,
+                                                            "total": 0.0012169280000762228,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0036255540005640796,
+                                                            "self": 0.0003886250001414737,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0015565609994609986,
+                                                                    "total": 0.0008283029999347491,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0015565609994609986
+                                                                    "self": 0.0008283029999347491
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.034427456000003076,
+                                                            "total": 0.017391022000083467,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005935189997217094,
+                                                            "self": 0.0003446420003001549,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003926330000467715,
+                                                                    "total": 0.0002456879999499506,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003926330000467715
+                                                                    "self": 0.0002456879999499506
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03166791900002863,
+                                                                    "total": 0.015950279999970007,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03166791900002863
+                                                                    "self": 0.015950279999970007
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017733850002059626,
+                                                                    "total": 0.0008504119998633541,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003576410003915953,
+                                                                    "self": 0.00018180899996877997,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014157439998143673,
+                                                                            "total": 0.0006686029998945742,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014157439998143673
+                                                                            "self": 0.0006686029998945742
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 191.2492107370008,
-                                                    "count": 18199,
+                                                    "total": 94.39136264501985,
+                                                    "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 9.557502959979274,
+                                                    "self": 3.6992152049976994,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.185447459006127,
-                                                            "count": 18199,
+                                                            "total": 2.0660426019983333,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 5.185447459006127
+                                                            "self": 2.0660426019983333
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 146.00484572101232,
-                                                            "count": 18199,
+                                                            "total": 77.33828555702075,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 146.00484572101232
+                                                            "self": 77.33828555702075
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 30.501414597003077,
-                                                            "count": 18199,
+                                                            "total": 11.287819281003067,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 5.439142806043719,
+                                                            "self": 2.2710576070865045,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 25.062271790959358,
-                                                                    "count": 181990,
+                                                                    "total": 9.016761673916562,
+                                                                    "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 25.062271790959358
+                                                                    "self": 9.016761673916562
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 109.81366847300092,
-                            "count": 18200,
-                            "self": 0.3968562949974057,
+                            "total": 42.147832241998,
+                            "count": 18192,
+                            "self": 0.26467858001501554,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 21.12404098500201,
-                                    "count": 18200,
-                                    "self": 20.670976952001865,
+                                    "total": 13.53277166398334,
+                                    "count": 18192,
+                                    "self": 13.274490549983511,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.4530640330001461,
+                                            "total": 0.25828111399982845,
                                             "count": 4,
-                                            "self": 0.4530640330001461
+                                            "self": 0.25828111399982845
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 88.2927711930015,
-                                    "count": 90,
-                                    "self": 35.169201176006936,
+                                    "total": 28.350381997999648,
+                                    "count": 19,
+                                    "self": 22.547381198998664,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 53.12357001699456,
-                                            "count": 4590,
-                                            "self": 53.12357001699456
+                                            "total": 5.8030007990009835,
+                                            "count": 570,
+                                            "self": 5.8030007990009835
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.440000212634914e-07,
+                    "total": 1.2429998150764732e-06,
                     "count": 1,
-                    "self": 9.440000212634914e-07
+                    "self": 1.2429998150764732e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.07698598899992248,
+                    "total": 0.07427533999998559,
                     "count": 1,
-                    "self": 0.0008022409997465729,
+                    "self": 0.00045179900007497054,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.07618374800017591,
+                            "total": 0.07382354099991062,
                             "count": 1,
-                            "self": 0.07618374800017591
+                            "self": 0.07382354099991062
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,28 +2,28 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 49952,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49952.onnx",
-                "reward": 14.0,
-                "creation_time": 1756517373.505935,
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 6.181818181818182,
+                "creation_time": 1756743693.4427552,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49952.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             },
             {
-                "steps": 99896,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.onnx",
-                "reward": null,
-                "creation_time": 1756517472.3510087,
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 8.878787878787879,
+                "creation_time": 1756743740.8214815,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
                 ]
             },
             {
                 "steps": 149984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": null,
-                "creation_time": 1756517572.436755,
+                "reward": 12.636363636363637,
+                "creation_time": 1756743786.9100819,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
                 ]
@@ -31,29 +31,29 @@
             {
                 "steps": 199984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 26.875,
-                "creation_time": 1756517669.422552,
+                "reward": null,
+                "creation_time": 1756743832.776409,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
-                "steps": 200200,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.onnx",
-                "reward": 25.90909090909091,
-                "creation_time": 1756517669.5180182,
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": null,
+                "creation_time": 1756743832.8569334,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200200,
+            "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 25.90909090909091,
-            "creation_time": 1756517669.5180182,
+            "reward": null,
+            "creation_time": 1756743832.8569334,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },