First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbdcace35d846ff6263002cafd6ac0476b161b62457352bc6d45d3cb09d0e803
+oid sha256:e339976f0a7b7d9ffbfa5fc5ef305b711807feef5fdda2a1cc891d545dbd71bd
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19dbc7f59581eefd859b98f43b5199b4c8859c1d731ccbd120c2614c40010387
+oid sha256:7cd97c7b1b8c1bb85118778ee972e8fb9865094505b723d7647fd1601324455e
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e18112cfcc4180079472b201868e60aa00804473229dd3d0686e0202d74fa327
+oid sha256:b88b13b745b3bc700e870c7c18d587dbe0d2cc6d92310d995fb5f97ec9bf9ec7
 size 3849902

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbdcace35d846ff6263002cafd6ac0476b161b62457352bc6d45d3cb09d0e803
+oid sha256:e339976f0a7b7d9ffbfa5fc5ef305b711807feef5fdda2a1cc891d545dbd71bd
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26977ba532a733a2469813b9d0a7920b9133c708e18cd541c17f3a10cccdd19e
+oid sha256:ffc77167a4680bcfcfaba77a79dafe3a5c3e21629a3f703117c29de4d47e9046
 size 3849902

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbdcace35d846ff6263002cafd6ac0476b161b62457352bc6d45d3cb09d0e803
+oid sha256:e339976f0a7b7d9ffbfa5fc5ef305b711807feef5fdda2a1cc891d545dbd71bd
 size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:013097f438ad8df65d3769dead6010bf396b49c44cefbd3ca6c27450dea4644e
+oid sha256:9f6912820298db9788707da00dc1135fcfee991841560316174528cd60c2aef2
 size 3849902

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2b3f8b1f163341040ee350746a2cf171fb4294ab2f709b51cb9b4a6c0d1ea1c
+oid sha256:9342bafbbe06ed741a98cebbf4a82082c1e048e2080a4b28eeb7469d9f4cc2a8
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e5b3a6cdf4e404901c708924301c3526a92950846578317a84a4dd7d23d9908
+oid sha256:b90d2c460e12f14d89388afca28b7c807f7484c5e69ab234ced1344b418166cf
 size 3849827

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b7c11bc10a9de4adb3d9dd0d7553353e12b595d6f546b3a7ea3a39abb90c30c
+oid sha256:4e4fd33daf917a72d2bb76921ab76ffe7a6f4ac9bd4ff9aced7167d1f01d5614
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57199a7dcce06017de5ce9abbc75c0518fd5cbb892c1d9969c947d17a3be768e
+oid sha256:16087e9a64b65951367607f0787ed0cbf56f1cf345b7411865741753d47dd898
 size 3849827

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:746ad920935e1af4a213d954ab357ede2bd9bf28040f88bbc5fd7bcc4654c5d9
+oid sha256:a6488892d60bdac3afc790cf7541e06f5e91d774dd56834018eb5eb561b96a7d
 size 3849077

SnowballTarget/events.out.tfevents.1777974117.900a678047b4.6507.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373c59923b51d077611ae96f555c410b603561ee0bcb076ba8ed90037d3bc40a
+size 23637

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": 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": true, "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": 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": 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

@@ -70,7 +70,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: false
-  force: true
+  force: false
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -2,6 +2,9 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
 Mono config path = '/content/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
+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
 Forcing GfxDevice: Null
@@ -31,7 +34,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.088 seconds
+- Completed reload, in  0.189 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)
@@ -42,7 +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: 0.718854 ms
+UnloadTime: 0.785120 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.
@@ -166,7 +169,7 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 42
+  Peak main deferred allocation count 40
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
@@ -175,13 +178,13 @@ Memory Statistics:
       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 6.7 MB
+      Peak Allocated memory 7.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
       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 17.7 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
@@ -210,10 +213,10 @@ 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]: 4762 frames, [64.0 KB-128.0 KB]: 696 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 3523 frames, [64.0 KB-128.0 KB]: 1935 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.8 KB
+      Peak Allocated memory 68.2 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
       Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames

run_logs/timers.json

@@ -2,15 +2,15 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.7619146108627319,
-            "min": 0.7603350877761841,
-            "max": 2.854929208755493,
+            "value": 0.9476588368415833,
+            "min": 0.9473971128463745,
+            "max": 2.827476739883423,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 7241.236328125,
-            "min": 7241.236328125,
-            "max": 29143.1171875,
+            "value": 9006.5498046875,
+            "min": 9006.5498046875,
+            "max": 28862.8828125,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
@@ -26,39 +26,39 @@
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.84373950958252,
-            "min": 0.5059031248092651,
-            "max": 12.863655090332031,
+            "value": 12.02534008026123,
+            "min": 0.4024864137172699,
+            "max": 12.02534008026123,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2504.529296875,
-            "min": 98.14520263671875,
-            "max": 2624.185546875,
+            "value": 2344.94140625,
+            "min": 78.08236694335938,
+            "max": 2424.51904296875,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07447079658638411,
-            "min": 0.06410284366198434,
-            "max": 0.07530805273392402,
+            "value": 0.06732845620678621,
+            "min": 0.060337600276826005,
+            "max": 0.07665276413243584,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.29788318634553645,
-            "min": 0.257156626387287,
-            "max": 0.3595227084736632,
+            "value": 0.26931382482714483,
+            "min": 0.24135040110730402,
+            "max": 0.36281541069083867,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.20726350263929832,
-            "min": 0.13972519677104978,
-            "max": 0.2870241140618044,
+            "value": 0.20387081758064382,
+            "min": 0.1358710084961928,
+            "max": 0.27533313785405716,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.8290540105571933,
-            "min": 0.5589007870841991,
-            "max": 1.3327619553196663,
+            "value": 0.8154832703225753,
+            "min": 0.5434840339847712,
+            "max": 1.2907533081723195,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 24.727272727272727,
-            "min": 3.909090909090909,
-            "max": 25.568181818181817,
+            "value": 23.795454545454547,
+            "min": 3.227272727272727,
+            "max": 23.977272727272727,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1088.0,
-            "min": 172.0,
-            "max": 1397.0,
+            "value": 1047.0,
+            "min": 142.0,
+            "max": 1271.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 24.727272727272727,
-            "min": 3.909090909090909,
-            "max": 25.568181818181817,
+            "value": 23.795454545454547,
+            "min": 3.227272727272727,
+            "max": 23.977272727272727,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1088.0,
-            "min": 172.0,
-            "max": 1397.0,
+            "value": 1047.0,
+            "min": 142.0,
+            "max": 1271.0,
             "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1777968570",
-        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
+        "start_time_seconds": "1777974116",
+        "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
         "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": "1777969030"
+        "end_time_seconds": "1777974591"
     },
-    "total": 459.4421793720003,
+    "total": 474.566383847,
     "count": 1,
-    "self": 0.429210881000472,
+    "self": 0.4834234700001616,
     "children": {
         "run_training.setup": {
-            "total": 0.024356959000215284,
+            "total": 0.02700582499983284,
             "count": 1,
-            "self": 0.024356959000215284
+            "self": 0.02700582499983284
         },
         "TrainerController.start_learning": {
-            "total": 458.9886115319996,
+            "total": 474.055954552,
             "count": 1,
-            "self": 0.3561200710164485,
+            "self": 0.42614270098556517,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.9803365249999842,
+                    "total": 3.258015984999929,
                     "count": 1,
-                    "self": 1.9803365249999842
+                    "self": 3.258015984999929
                 },
                 "TrainerController.advance": {
-                    "total": 456.571469220984,
+                    "total": 470.2912310030147,
                     "count": 18192,
-                    "self": 0.3756143500058897,
+                    "self": 0.43143699002689573,
                     "children": {
                         "env_step": {
-                            "total": 334.7971753100037,
+                            "total": 342.673843478997,
                             "count": 18192,
-                            "self": 262.42748001199834,
+                            "self": 265.4326973299717,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 72.15000229601628,
+                                    "total": 76.99555055901897,
                                     "count": 18192,
-                                    "self": 1.3123068910272195,
+                                    "self": 1.3980525890219724,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 70.83769540498906,
+                                            "total": 75.597497969997,
                                             "count": 18192,
-                                            "self": 70.83769540498906
+                                            "self": 75.597497969997
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.2196930019890715,
+                                    "total": 0.24559559000636,
                                     "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 457.12734604594334,
+                                            "total": 472.2407024960055,
                                             "count": 18192,
                                             "is_parallel": true,
-                                            "self": 226.15448401198228,
+                                            "self": 240.1246171360158,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.00217364699983591,
+                                                            "total": 0.004395901999941998,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007151379995775642,
+                                                            "self": 0.0030559089998405398,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0014585090002583456,
+                                                                    "total": 0.0013399930001014582,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014585090002583456
+                                                                    "self": 0.0013399930001014582
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03823596100028226,
+                                                            "total": 0.0371842160000142,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006233019994397182,
+                                                            "self": 0.0006975230003263277,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004009060003227205,
+                                                                    "total": 0.00044638099984695145,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004009060003227205
+                                                                    "self": 0.00044638099984695145
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.035229632000664424,
+                                                                    "total": 0.03368340099996203,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.035229632000664424
+                                                                    "self": 0.03368340099996203
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001982120999855397,
+                                                                    "total": 0.0023569109998788917,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003798630004894221,
+                                                                    "self": 0.00046562699981222977,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0016022579993659747,
+                                                                            "total": 0.001891284000066662,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0016022579993659747
+                                                                            "self": 0.001891284000066662
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 230.97286203396106,
+                                                    "total": 232.1160853599897,
                                                     "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 10.639755019946278,
+                                                    "self": 10.71805155799916,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.7760944390183795,
+                                                            "total": 5.796521700990979,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 5.7760944390183795
+                                                            "self": 5.796521700990979
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 175.27033442499214,
+                                                            "total": 176.50556602198276,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 175.27033442499214
+                                                            "self": 176.50556602198276
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 39.28667815000426,
+                                                            "total": 39.09594607901681,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 6.855326655922909,
+                                                            "self": 6.961498372000051,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 32.431351494081355,
+                                                                    "total": 32.13444770701676,
                                                                     "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 32.431351494081355
+                                                                    "self": 32.13444770701676
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 121.39867956097441,
+                            "total": 127.18595053399076,
                             "count": 18192,
-                            "self": 0.45243304096584325,
+                            "self": 0.5425558589888624,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 26.900470545004282,
+                                    "total": 28.026655043001483,
                                     "count": 18192,
-                                    "self": 26.495559609003067,
+                                    "self": 27.579495239001517,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.4049109360012153,
+                                            "total": 0.44715980399996624,
                                             "count": 4,
-                                            "self": 0.4049109360012153
+                                            "self": 0.44715980399996624
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 94.04577597500429,
+                                    "total": 98.61673963200042,
                                     "count": 90,
-                                    "self": 38.71959435799636,
+                                    "self": 40.20500799399542,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 55.32618161700793,
+                                            "total": 58.411731638004994,
                                             "count": 4587,
-                                            "self": 55.32618161700793
+                                            "self": 58.411731638004994
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.099994713324122e-07,
+                    "total": 1.503000021330081e-06,
                     "count": 1,
-                    "self": 9.099994713324122e-07
+                    "self": 1.503000021330081e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08068480499969155,
+                    "total": 0.08056335999981457,
                     "count": 1,
-                    "self": 0.0010251459998471546,
+                    "self": 0.0007189929997366562,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.0796596589998444,
+                            "total": 0.07984436700007791,
                             "count": 1,
-                            "self": 0.0796596589998444
+                            "self": 0.07984436700007791
                         }
                     }
                 }

run_logs/training_status.json

@@ -4,8 +4,8 @@
             {
                 "steps": 49936,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 14.090909090909092,
-                "creation_time": 1777968688.1580577,
+                "reward": 14.0,
+                "creation_time": 1777974232.200192,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
                 ]
@@ -13,8 +13,8 @@
             {
                 "steps": 99960,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 22.272727272727273,
-                "creation_time": 1777968803.004159,
+                "reward": 19.454545454545453,
+                "creation_time": 1777974344.4747741,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
                 ]
@@ -22,8 +22,8 @@
             {
                 "steps": 149984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 23.09090909090909,
-                "creation_time": 1777968917.1218488,
+                "reward": 22.90909090909091,
+                "creation_time": 1777974466.117128,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
                 ]
@@ -31,8 +31,8 @@
             {
                 "steps": 199984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 24.545454545454547,
-                "creation_time": 1777969029.7741652,
+                "reward": 23.181818181818183,
+                "creation_time": 1777974590.7718866,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
@@ -40,8 +40,8 @@
             {
                 "steps": 200112,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 24.545454545454547,
-                "creation_time": 1777969029.8655777,
+                "reward": 23.181818181818183,
+                "creation_time": 1777974590.8645546,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
@@ -50,8 +50,8 @@
         "final_checkpoint": {
             "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 24.545454545454547,
-            "creation_time": 1777969029.8655777,
+            "reward": 23.181818181818183,
+            "creation_time": 1777974590.8645546,
             "auxillary_file_paths": [
                 "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]