First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbb11df9c6cabe37d7b803d12e674a49505f678f04a303ef87dd6a6ad5418df5
+oid sha256:7c074b0288b91b7cef607f42ff1a0edbe51a419cefd79fe519a413c2a70a1ee5
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecccd296114f695770e1c25656fc571344f77242dae19b669b84bc3a82c757b7
+oid sha256:466e9c4627f4b89cdc86dbd58ca6ad189221fda96da79493cd7d9aa31d20fef9
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d40fa4ac252dc3a34a69688069215eb657ba9d7f54612300c2d074d4fbb9db3a
+oid sha256:d12a70bcf52f9555f92e153a11a422a5ff7bd17f4d94387b1767f2ecc62cd66b
 size 3849902

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbb11df9c6cabe37d7b803d12e674a49505f678f04a303ef87dd6a6ad5418df5
+oid sha256:7c074b0288b91b7cef607f42ff1a0edbe51a419cefd79fe519a413c2a70a1ee5
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7bdde7f8374d2271161f031d5bdb1120b61f5576fe6180b0005240d34dee1cf
+oid sha256:a32bee4362fa42f0600eb85b6a52196c3c2606b47a487603e69b38c0a7d32663
 size 3849902

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbb11df9c6cabe37d7b803d12e674a49505f678f04a303ef87dd6a6ad5418df5
+oid sha256:7c074b0288b91b7cef607f42ff1a0edbe51a419cefd79fe519a413c2a70a1ee5
 size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a473c1d4af528f7e38b3d05565af7c24f6ae110c8800b8abbc0430fc4bcaf33
+oid sha256:69731f1ef379362c6ee7ac04ae2f589ae0a3d2f613d07a84683d2ebfb2b48645
 size 3849902

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcddd4b2ab615cf4c406d4224a4c287043e44b75480808d2933e93565ac44653
+oid sha256:54e586c6a8fc555fbf5c0e375d3f44d1044a41c444e22befdc2af7f72fdec4ee
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45976696c839b97439392fff4a37e79c42587d101267bb986bbcf6680d492854
+oid sha256:1c53a1b087c40d0c76b920af7979bcaee2c981eb020a16ad3e5befc62ba71974
 size 3849827

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a832328808b09ef10b406ef1ed6b285bcd5e44c936c23224636252e685cf5d0
+oid sha256:0cc93a21b833f96dc56b885154560cfd8ea294ec17810388c91dd60efcaa6d7c
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec6820f30d62d8e27eabdfcf1a4940fee99251f9dc8d3b32fe3c152cce91738
+oid sha256:c8f6b37f3572c4816cf80c17d88fcc3202a351d4de8f83e333027adcf7124582
 size 3849827

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41a6c414bd1ce5723b6953f2677782278a486a10cd0e90029f3e6dcea2efb54e
+oid sha256:886bb8c30f0bab31ffbd8fe7df822147f6427b24e0640002b2c53766717b5524
 size 3849077

SnowballTarget/events.out.tfevents.1783022792.8dd7c3fe047b.22523.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15645e20708ef7bfb3eb0b2c81b85dc1fd86ccd36ceac428952c6990245def9d
+size 23317

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": 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": 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": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -66,11 +66,11 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: SnowballTarget2
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -2,9 +2,6 @@ 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
@@ -34,7 +31,7 @@ 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  0.082 seconds
+- Completed reload, in  0.118 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)
@@ -45,7 +42,7 @@ 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: 0.686695 ms
+UnloadTime: 0.814736 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.
@@ -169,7 +166,7 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 41
+  Peak main deferred allocation count 42
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
@@ -184,7 +181,7 @@ Memory Statistics:
       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 17.3 MB
+      Peak Allocated memory 17.2 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -213,7 +210,7 @@ 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]: 4350 frames, [64.0 KB-128.0 KB]: 1108 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4919 frames, [64.0 KB-128.0 KB]: 539 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 66.8 KB

run_logs/timers.json

@@ -2,15 +2,15 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.8953462839126587,
-            "min": 0.8953462839126587,
-            "max": 2.842545747756958,
+            "value": 0.7170038819313049,
+            "min": 0.7170038819313049,
+            "max": 2.849374532699585,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8509.37109375,
-            "min": 8509.37109375,
-            "max": 29016.70703125,
+            "value": 6814.40478515625,
+            "min": 6814.40478515625,
+            "max": 29086.416015625,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
@@ -26,39 +26,39 @@
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.430351257324219,
-            "min": 0.3850409984588623,
-            "max": 12.430351257324219,
+            "value": 12.871124267578125,
+            "min": 0.31479066610336304,
+            "max": 12.871124267578125,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2423.91845703125,
-            "min": 74.69795227050781,
-            "max": 2511.078125,
+            "value": 2509.869140625,
+            "min": 61.06938934326172,
+            "max": 2610.96142578125,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06207742861828164,
-            "min": 0.06207742861828164,
-            "max": 0.07503259427875153,
+            "value": 0.07426913766177641,
+            "min": 0.062340034129567144,
+            "max": 0.07728020640694441,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.24830971447312655,
-            "min": 0.24830971447312655,
-            "max": 0.37516297139375765,
+            "value": 0.29707655064710564,
+            "min": 0.24936013651826858,
+            "max": 0.38640103203472204,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.21889654324189123,
-            "min": 0.12068470898791965,
-            "max": 0.27420273843933557,
+            "value": 0.19394765940367006,
+            "min": 0.12874440204434318,
+            "max": 0.2811643300103206,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.8755861729675649,
-            "min": 0.4827388359516786,
-            "max": 1.3710136921966778,
+            "value": 0.7757906376146803,
+            "min": 0.5149776081773727,
+            "max": 1.3864895006020863,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 24.477272727272727,
-            "min": 3.25,
-            "max": 24.836363636363636,
+            "value": 25.454545454545453,
+            "min": 3.5454545454545454,
+            "max": 25.681818181818183,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1077.0,
-            "min": 143.0,
-            "max": 1366.0,
+            "value": 1120.0,
+            "min": 156.0,
+            "max": 1392.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 24.477272727272727,
-            "min": 3.25,
-            "max": 24.836363636363636,
+            "value": 25.454545454545453,
+            "min": 3.5454545454545454,
+            "max": 25.681818181818183,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1077.0,
-            "min": 143.0,
-            "max": 1366.0,
+            "value": 1120.0,
+            "min": 156.0,
+            "max": 1392.0,
             "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1783021245",
+        "start_time_seconds": "1783022791",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics --force",
         "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": "1783021701"
+        "end_time_seconds": "1783023580"
     },
-    "total": 455.7827961459993,
+    "total": 789.139154603,
     "count": 1,
-    "self": 0.39008450199935396,
+    "self": 0.9505620250001812,
     "children": {
         "run_training.setup": {
-            "total": 0.025760945999991236,
+            "total": 0.03804915199998504,
             "count": 1,
-            "self": 0.025760945999991236
+            "self": 0.03804915199998504
         },
         "TrainerController.start_learning": {
-            "total": 455.366950698,
+            "total": 788.1505434259998,
             "count": 1,
-            "self": 0.3623665289837845,
+            "self": 0.5642361140489811,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.16832735700018,
+                    "total": 3.984056598999814,
                     "count": 1,
-                    "self": 3.16832735700018
+                    "self": 3.984056598999814
                 },
                 "TrainerController.advance": {
-                    "total": 451.75691105701526,
+                    "total": 783.3918465949519,
                     "count": 18192,
-                    "self": 0.37170535098948676,
+                    "self": 0.5569624301406293,
                     "children": {
                         "env_step": {
-                            "total": 331.6649022980405,
+                            "total": 593.9856056248818,
                             "count": 18192,
-                            "self": 260.30505294407067,
+                            "self": 488.390564265801,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 71.14122668900518,
+                                    "total": 105.25798858102007,
                                     "count": 18192,
-                                    "self": 1.28271398905963,
+                                    "self": 1.8763829380568495,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 69.85851269994555,
+                                            "total": 103.38160564296322,
                                             "count": 18192,
-                                            "self": 69.85851269994555
+                                            "self": 103.38160564296322
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.21862266496464144,
+                                    "total": 0.33705277806075173,
                                     "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 453.45986310100943,
+                                            "total": 780.7887304509841,
                                             "count": 18192,
                                             "is_parallel": true,
-                                            "self": 224.29435286400758,
+                                            "self": 352.06102459597514,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005188700999951834,
+                                                            "total": 0.004853637000451272,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0038084029997662583,
+                                                            "self": 0.0007601290008096839,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013802980001855758,
+                                                                    "total": 0.004093507999641588,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013802980001855758
+                                                                    "self": 0.004093507999641588
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06694399100024384,
+                                                            "total": 0.09955226599959133,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005868170001122053,
+                                                            "self": 0.0006345179999698303,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004256540000824316,
+                                                                    "total": 0.0023351079998974456,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004256540000824316
+                                                                    "self": 0.0023351079998974456
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.06197148899991589,
+                                                                    "total": 0.08962097899984656,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.06197148899991589
+                                                                    "self": 0.08962097899984656
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.003960031000133313,
+                                                                    "total": 0.006961660999877495,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003488140000627027,
+                                                                    "self": 0.0003846850022455328,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.00361121700007061,
+                                                                            "total": 0.006576975997631962,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.00361121700007061
+                                                                            "self": 0.006576975997631962
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 229.16551023700185,
+                                                    "total": 428.72770585500894,
                                                     "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 10.392895890114232,
+                                                    "self": 12.516839495273416,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.577040021977609,
+                                                            "total": 5.7071867639260745,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 5.577040021977609
+                                                            "self": 5.7071867639260745
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 175.30952451693793,
+                                                            "total": 340.036357533967,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 175.30952451693793
+                                                            "self": 340.036357533967
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 37.886049807972086,
+                                                            "total": 70.46732206184242,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 6.776479363983526,
+                                                            "self": 12.606582177909331,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 31.10957044398856,
+                                                                    "total": 57.86073988393309,
                                                                     "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 31.10957044398856
+                                                                    "self": 57.86073988393309
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 119.72030340798528,
+                            "total": 188.8492785399294,
                             "count": 18192,
-                            "self": 0.4323178519848625,
+                            "self": 0.7245181098915054,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 24.243671139999606,
+                                    "total": 38.977636828044524,
                                     "count": 18192,
-                                    "self": 23.83447385699901,
+                                    "self": 38.19412665204436,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.4091972830005943,
+                                            "total": 0.7835101760001635,
                                             "count": 4,
-                                            "self": 0.4091972830005943
+                                            "self": 0.7835101760001635
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 95.04431441600082,
+                                    "total": 149.14712360199337,
                                     "count": 90,
-                                    "self": 39.90401564700869,
+                                    "self": 71.63568960995963,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 55.140298768992125,
+                                            "total": 77.51143399203374,
                                             "count": 4587,
-                                            "self": 55.140298768992125
+                                            "self": 77.51143399203374
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.880006134859286e-07,
+                    "total": 1.27099974633893e-06,
                     "count": 1,
-                    "self": 8.880006134859286e-07
+                    "self": 1.27099974633893e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.07934486700014531,
+                    "total": 0.21040284699938638,
                     "count": 1,
-                    "self": 0.0007445010005540098,
+                    "self": 0.0009470219993090723,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.0786003659995913,
+                            "total": 0.2094558250000773,
                             "count": 1,
-                            "self": 0.0786003659995913
+                            "self": 0.2094558250000773
                         }
                     }
                 }

run_logs/training_status.json

@@ -3,57 +3,57 @@
         "checkpoints": [
             {
                 "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 14.727272727272727,
-                "creation_time": 1783021361.3297844,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 17.363636363636363,
+                "creation_time": 1783022988.6344864,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             },
             {
                 "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 20.90909090909091,
-                "creation_time": 1783021475.3236094,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 23.727272727272727,
+                "creation_time": 1783023191.540275,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
                 ]
             },
             {
                 "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 23.818181818181817,
-                "creation_time": 1783021588.0639477,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 23.90909090909091,
+                "creation_time": 1783023383.856865,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
                 ]
             },
             {
                 "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.0,
-                "creation_time": 1783021700.8005352,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 26.818181818181817,
+                "creation_time": 1783023579.5983684,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
                 "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.0,
-                "creation_time": 1783021700.8900487,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 26.818181818181817,
+                "creation_time": 1783023579.831131,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
             "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 25.0,
-            "creation_time": 1783021700.8900487,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 26.818181818181817,
+            "creation_time": 1783023579.831131,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },