First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d938257ea9b1870cf6859c624c5c540ef9a1ab9ed9d5f3001a621ac25542a1
-size 264598
+oid sha256:e70e734b200138695e2c3013c6b01ea46b0bdbfb789cd6a2d914b5c2a22159a5
+size 197609

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09de72421345c39129447ec5003f5dd14d284dfd30c2704b1c8f4f54bcf455ab
-size 264598
+oid sha256:4087d4a7a0ed98d1e30efb9f197837917e8f2d9c97288fc76ef1e18ce28ab7c1
+size 197609

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42bb3df25d8d6de104f0ed22852586047f3e13a145f5f34a6445f6e9be3bb837
-size 1544475
+oid sha256:8d00c4fb53bba706a4ee1412a2ecf30b59ebb95b44cde3717405557ec17acb9a
+size 1143083

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d938257ea9b1870cf6859c624c5c540ef9a1ab9ed9d5f3001a621ac25542a1
-size 264598
+oid sha256:e70e734b200138695e2c3013c6b01ea46b0bdbfb789cd6a2d914b5c2a22159a5
+size 197609

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b416f094481124d1da3dc25879896e05772c57d14b027a4e483be0bef568d082
-size 1544475
+oid sha256:e59e3b48b3632af015dc6a38d494f7012193f598d910e738054d7cd6ed1f7986
+size 1143083

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d938257ea9b1870cf6859c624c5c540ef9a1ab9ed9d5f3001a621ac25542a1
-size 264598
+oid sha256:e70e734b200138695e2c3013c6b01ea46b0bdbfb789cd6a2d914b5c2a22159a5
+size 197609

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c70769c8643a97f7b55aca345dd97f433175deef49edaf0324d5d730f3837b7d
-size 1544475
+oid sha256:f7fb6ef6b172f1eadbff31c6925e4513ba82008335bb9b4424bb74f0c71185b3
+size 1143083

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f995e3e69bf1ba3ed02ad0d60ba06a9ea03571be559880ed092cd05060cc8883
-size 264598
+oid sha256:3f59101234824e69a1e30affe873939cf91feda1d9569ad4d6337f5454908aee
+size 197609

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a5536bb30d0c0b3cc1ec3161c3d4e389253d0805949f471dbd290adb64116fa
-size 1544400
+oid sha256:8a936a93043a0c9f56609711c4cb61cdaa67e9ac49e516318031b192dce4f190
+size 1143024

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a35219a02ea7599a3b07de633978c20bc8c81ce20ebcb62e2fb5c6da13b10458
-size 264598
+oid sha256:9a72c03cf6ff0266f090beada747ed9b9b8f77bf7d4dd8f705d08eca0b624d21
+size 197609

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:badb821167cd897b7f8fa154bd0c191def4c4d6b72f1468160e398e4191c324e
-size 1544400
+oid sha256:93eee4b58a589ec491dc73f7f02cdd7610b814c9ec78b12e7412f3ec6606568b
+size 1143024

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2723edb484b0f4aba46a1c5ad81721fce616e524f729e9cd825290d5239468a
-size 1543650
+oid sha256:9dffe09e55ac946610eff28dadb707e1fb3fefda92474971427adbf8ff6b69ef
+size 1142434

SnowballTarget/events.out.tfevents.1716710689.9bd833adf9b7.9473.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:217d3c2ee94f27aa8c2318268fd87c7d3f127f059423550d7a1040c4b183e372
+size 23378

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": 128, "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": true, "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": 0.0006, "beta": 0.005, "epsilon": 0.3, "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": 128, "num_layers": 1, "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": true, "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": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -5,9 +5,9 @@ behaviors:
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
-      learning_rate: 0.0003
+      learning_rate: 0.0006
       beta: 0.005
-      epsilon: 0.2
+      epsilon: 0.3
       lambd: 0.95
       num_epoch: 3
       shared_critic: false
@@ -18,7 +18,7 @@ behaviors:
     network_settings:
       normalize: false
       hidden_units: 128
-      num_layers: 2
+      num_layers: 1
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
@@ -66,7 +66,7 @@ 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

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  0.090 seconds
+- Completed reload, in  0.088 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: 0.708141 ms
+UnloadTime: 0.817515 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 48
+  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]: 5460 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.8 MB
+      Peak Allocated memory 17.4 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]: 2342 frames, [64.0 KB-128.0 KB]: 3118 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4437 frames, [64.0 KB-128.0 KB]: 1023 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 68.2 KB

run_logs/timers.json

@@ -2,15 +2,15 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.9592263698577881,
-            "min": 0.9592263698577881,
-            "max": 2.8673253059387207,
+            "value": 1.0069396495819092,
+            "min": 1.0069396495819092,
+            "max": 2.810028076171875,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 9158.693359375,
-            "min": 9158.693359375,
-            "max": 29364.27734375,
+            "value": 9614.259765625,
+            "min": 9614.259765625,
+            "max": 28808.408203125,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 10.5465669631958,
-            "min": 0.2594470679759979,
-            "max": 10.5465669631958,
+            "value": 12.656725883483887,
+            "min": 0.31081098318099976,
+            "max": 12.656725883483887,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2056.58056640625,
-            "min": 50.332733154296875,
-            "max": 2145.73486328125,
+            "value": 2468.0615234375,
+            "min": 60.297332763671875,
+            "max": 2568.51611328125,
             "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,51 +50,51 @@
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06805259152201425,
-            "min": 0.060415040380629594,
-            "max": 0.07521182519335794,
+            "value": 0.06861288506586467,
+            "min": 0.057799714654524284,
+            "max": 0.0758767314015559,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.272210366088057,
-            "min": 0.24166016152251837,
-            "max": 0.3760591259667897,
+            "value": 0.2744515402634587,
+            "min": 0.23119885861809714,
+            "max": 0.36978030635623776,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.19439689347556993,
-            "min": 0.11510944564817657,
-            "max": 0.28371769642713024,
+            "value": 0.23546830710827138,
+            "min": 0.1087834547700671,
+            "max": 0.281679127146216,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7775875739022797,
-            "min": 0.4604377825927063,
-            "max": 1.3012281764371723,
+            "value": 0.9418732284330855,
+            "min": 0.4351338190802684,
+            "max": 1.4048231445691166,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
+            "value": 1.616409730600001e-05,
+            "min": 1.616409730600001e-05,
+            "max": 0.0005837640027059999,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
+            "value": 6.465638922400003e-05,
+            "min": 6.465638922400003e-05,
+            "max": 0.00277032003828,
             "count": 20
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
+            "value": 0.10538800000000001,
+            "min": 0.10538800000000001,
+            "max": 0.29458799999999996,
             "count": 20
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
+            "value": 0.42155200000000004,
+            "min": 0.42155200000000004,
+            "max": 1.42344,
             "count": 20
         },
         "SnowballTarget.Policy.Beta.mean": {
@@ -110,27 +110,27 @@
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 20.454545454545453,
-            "min": 3.4545454545454546,
-            "max": 20.963636363636365,
+            "value": 24.681818181818183,
+            "min": 3.1136363636363638,
+            "max": 24.963636363636365,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 900.0,
-            "min": 152.0,
-            "max": 1153.0,
+            "value": 1086.0,
+            "min": 137.0,
+            "max": 1373.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 20.454545454545453,
-            "min": 3.4545454545454546,
-            "max": 20.963636363636365,
+            "value": 24.681818181818183,
+            "min": 3.1136363636363638,
+            "max": 24.963636363636365,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 900.0,
-            "min": 152.0,
-            "max": 1153.0,
+            "value": 1086.0,
+            "min": 137.0,
+            "max": 1373.0,
             "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1716709400",
+        "start_time_seconds": "1716710688",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1716709912"
+        "end_time_seconds": "1716711189"
     },
-    "total": 512.6412643929999,
+    "total": 500.79940837000004,
     "count": 1,
-    "self": 0.43878520199996274,
+    "self": 0.47871936000046844,
     "children": {
         "run_training.setup": {
-            "total": 0.05917830900000354,
+            "total": 0.05563367099966854,
             "count": 1,
-            "self": 0.05917830900000354
+            "self": 0.05563367099966854
         },
         "TrainerController.start_learning": {
-            "total": 512.143300882,
+            "total": 500.2650553389999,
             "count": 1,
-            "self": 0.7142993330163563,
+            "self": 0.7109024630158274,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.43152223900006,
+                    "total": 2.115907714000059,
                     "count": 1,
-                    "self": 3.43152223900006
+                    "self": 2.115907714000059
                 },
                 "TrainerController.advance": {
-                    "total": 507.9135204049834,
+                    "total": 497.35660923498426,
                     "count": 18200,
-                    "self": 0.36656446498398054,
+                    "self": 0.3631436589657824,
                     "children": {
                         "env_step": {
-                            "total": 507.5469559399994,
+                            "total": 496.9934655760185,
                             "count": 18200,
-                            "self": 334.0687574500206,
+                            "self": 326.54533360395635,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 173.11749443499002,
+                                    "total": 170.0980387850159,
                                     "count": 18200,
-                                    "self": 1.739189724991661,
+                                    "self": 1.7037756250006169,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 171.37830470999836,
+                                            "total": 168.39426316001527,
                                             "count": 18200,
-                                            "self": 171.37830470999836
+                                            "self": 168.39426316001527
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.360704054988787,
+                                    "total": 0.35009318704624093,
                                     "count": 18200,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 510.5921331410249,
+                                            "total": 498.7785037659978,
                                             "count": 18200,
                                             "is_parallel": true,
-                                            "self": 253.65956471402967,
+                                            "self": 243.94271257897435,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005337968000048932,
+                                                            "total": 0.002219015999799012,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0037692930000048364,
+                                                            "self": 0.0006655649990534585,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0015686750000440952,
+                                                                    "total": 0.0015534510007455538,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0015686750000440952
+                                                                    "self": 0.0015534510007455538
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.08067132899998342,
+                                                            "total": 0.06019268000000011,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000674652000043352,
+                                                            "self": 0.0007173359999796958,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00040851999995084043,
+                                                                    "total": 0.0004115980000278796,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00040851999995084043
+                                                                    "self": 0.0004115980000278796
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.07444236799994997,
+                                                                    "total": 0.05698251200010418,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.07444236799994997
+                                                                    "self": 0.05698251200010418
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.005145789000039258,
+                                                                    "total": 0.0020812339998883544,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004383110001526802,
+                                                                    "self": 0.00039561100038554287,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.004707477999886578,
+                                                                            "total": 0.0016856229995028116,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.004707477999886578
+                                                                            "self": 0.0016856229995028116
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 256.9325684269952,
+                                                    "total": 254.83579118702346,
                                                     "count": 18199,
                                                     "is_parallel": true,
-                                                    "self": 11.641519734009876,
+                                                    "self": 11.347686508004244,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 6.083442166979921,
+                                                            "total": 6.006531404995712,
                                                             "count": 18199,
                                                             "is_parallel": true,
-                                                            "self": 6.083442166979921
+                                                            "self": 6.006531404995712
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 201.0750567190022,
+                                                            "total": 200.15692748401852,
                                                             "count": 18199,
                                                             "is_parallel": true,
-                                                            "self": 201.0750567190022
+                                                            "self": 200.15692748401852
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 38.132549807003215,
+                                                            "total": 37.32464579000498,
                                                             "count": 18199,
                                                             "is_parallel": true,
-                                                            "self": 7.608864475957148,
+                                                            "self": 7.39685486497774,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 30.523685331046067,
+                                                                    "total": 29.92779092502724,
                                                                     "count": 181990,
                                                                     "is_parallel": true,
-                                                                    "self": 30.523685331046067
+                                                                    "self": 29.92779092502724
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 4.045800005769706e-05,
+                    "total": 0.00013762099979430786,
                     "count": 1,
-                    "self": 4.045800005769706e-05,
+                    "self": 0.00013762099979430786,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 501.0140586449651,
-                                    "count": 777042,
+                                    "total": 491.2628267113032,
+                                    "count": 711357,
                                     "is_parallel": true,
-                                    "self": 16.66402842095124,
+                                    "self": 15.55820723330362,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 280.39488239801403,
-                                            "count": 777042,
+                                            "total": 275.542963600999,
+                                            "count": 711357,
                                             "is_parallel": true,
-                                            "self": 279.7035764020138,
+                                            "self": 275.0221872739994,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 0.6913059960002101,
+                                                    "total": 0.5207763269995667,
                                                     "count": 4,
                                                     "is_parallel": true,
-                                                    "self": 0.6913059960002101
+                                                    "self": 0.5207763269995667
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 203.9551478259998,
+                                            "total": 200.1616558770006,
                                             "count": 90,
                                             "is_parallel": true,
-                                            "self": 63.599881769004696,
+                                            "self": 62.33664410699612,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 140.3552660569951,
+                                                    "total": 137.8250117700045,
                                                     "count": 4587,
                                                     "is_parallel": true,
-                                                    "self": 140.3552660569951
+                                                    "self": 137.8250117700045
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08391844700008733,
+                    "total": 0.08149830599995767,
                     "count": 1,
-                    "self": 0.0006731150001542119,
+                    "self": 0.0008183389995792822,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08324533199993311,
+                            "total": 0.08067996700037838,
                             "count": 1,
-                            "self": 0.08324533199993311
+                            "self": 0.08067996700037838
                         }
                     }
                 }

run_logs/training_status.json

@@ -3,57 +3,57 @@
         "checkpoints": [
             {
                 "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 13.363636363636363,
-                "creation_time": 1716709532.1828399,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 15.272727272727273,
+                "creation_time": 1716710816.7560582,
                 "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": 18.09090909090909,
-                "creation_time": 1716709658.8884063,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 21.818181818181817,
+                "creation_time": 1716710941.0128334,
                 "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": 19.818181818181817,
-                "creation_time": 1716709786.4175732,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 23.818181818181817,
+                "creation_time": 1716711064.1459694,
                 "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": 20.181818181818183,
-                "creation_time": 1716709912.1630945,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 24.272727272727273,
+                "creation_time": 1716711188.941713,
                 "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": 20.181818181818183,
-                "creation_time": 1716709912.2806418,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 24.272727272727273,
+                "creation_time": 1716711189.0530596,
                 "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": 20.181818181818183,
-            "creation_time": 1716709912.2806418,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 24.272727272727273,
+            "creation_time": 1716711189.0530596,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },