First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:011386b75378b4c1b96c9c92a948a7d3ae7e0d490cb9b900b6ac8c77ed7a17af
+oid sha256:d80680a1d9f148a8b5b0bb8d278b4c95cd7b472914e525b8b4c34b2fef7d5dc1
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad93abc6559c42308d01bf5427fb8712e5177a3939ab66511faef00b915bbe3b
+oid sha256:718a7467bf1346480f744dc98c09882be3ff40423f45e66adcc644fdbb140ff3
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:794c7562291a6aabcdbddddd9c3a92b8f1ec76e81362e6f3e6948c2cd61682e2
+oid sha256:d113c578b1cf190ba57621d905115bcfe9b59e5544c727a475b937b3738d0d1b
 size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:011386b75378b4c1b96c9c92a948a7d3ae7e0d490cb9b900b6ac8c77ed7a17af
+oid sha256:d80680a1d9f148a8b5b0bb8d278b4c95cd7b472914e525b8b4c34b2fef7d5dc1
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b7057a9601f8b59b1a8a20f8f3c79dfb1000b1b2cf6099a79760331f6973dab
+oid sha256:30bda23c371b8e979ecbc9f3ec6e50cad72af686f7d4c974b9c43b2898377577
 size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3a1a44fd356b0789b0c31e857558c93ec00b2373f9fa5ac4ec93a8621804e9d
+oid sha256:d80680a1d9f148a8b5b0bb8d278b4c95cd7b472914e525b8b4c34b2fef7d5dc1
 size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:959f61c39b24d972b5dcc574224c177cc7bb41b530c93ce3468b1f5263aff8db
+oid sha256:3c2e20839578d2134359af43c614c0ed2d2eec4496cd59120a009acd1623a7f2
 size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09b14f5c05ef43018deca04dba39b831dea14c3e55a5b6004ff2d92618a3fff
+oid sha256:c039c241868b9890b05d65ec78f417dcece204a9f26c31c6586579703ee62951
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478d1a2f2f6814ba84987404750045ef3a430300366888e9a2d4ab978ee1345b
+oid sha256:75244e710f95f5eeda2c761d5bc981308446e7e8d36ced844c318d5748d8d85d
 size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c95f960feab1d1553489e18739240eb691c6002ce651c738d0127a935d5294d8
+oid sha256:7633ea1236b5fa9613885a37c1aff8ab1ddeacad735360d8093b222c3eff073d
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:199eb9ea2ce3dac030f350e8fec5981966bce635d183689654b78e5eda232bcd
+oid sha256:aa53aebc1490595a9a06048e66c4b8154f31ed08dd5cc000149def4f89219560
 size 3850000

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85bf41a1b006db04de200aca01567410f733c703a59d57aa17c5307ac0405412
+oid sha256:60b0a8b18e9b2a4a77d49d044b1fab929c7de880ebdf4aa07a65c25694bc2696
 size 3849250

SnowballTarget/events.out.tfevents.1701655279.b46918e9dea0.3129.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a345a0189d47e23ec6dcc65545a90c6f2561bc3e54d84e591c854cec2c73a99e
+size 18649

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": 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}
+{"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": 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}

configuration.yaml

@@ -66,7 +66,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget2
+  run_id: SnowballTarget1
   initialize_from: null
   load_model: false
   resume: false

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  0.132 seconds
+- Completed reload, in  0.084 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: 0.887110 ms
+UnloadTime: 0.642631 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 41
+  Peak main deferred allocation count 38
     [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]: 5461 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 6.7 MB
+      Peak Allocated memory 6.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
       Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.6 MB
+      Peak Allocated memory 17.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -210,7 +213,7 @@ 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]: 4798 frames, [64.0 KB-128.0 KB]: 663 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4734 frames, [64.0 KB-128.0 KB]: 727 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": 0.9833106994628906,
-            "min": 0.9833106994628906,
-            "max": 2.8693156242370605,
+            "value": 0.8856061697006226,
+            "min": 0.8785231709480286,
+            "max": 2.8686530590057373,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 9410.283203125,
-            "min": 9410.283203125,
-            "max": 29416.22265625,
+            "value": 8475.2509765625,
+            "min": 8475.2509765625,
+            "max": 29377.875,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.537129402160645,
-            "min": 0.4118865132331848,
-            "max": 12.537129402160645,
+            "value": 12.59672737121582,
+            "min": 0.2983435094356537,
+            "max": 12.755240440368652,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2444.740234375,
-            "min": 79.9059829711914,
-            "max": 2509.056884765625,
+            "value": 2456.36181640625,
+            "min": 57.87864303588867,
+            "max": 2589.71728515625,
             "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.0636769804950032,
-            "min": 0.06276891269231676,
-            "max": 0.07362485134845152,
+            "value": 0.06484215036428341,
+            "min": 0.06481837471345024,
+            "max": 0.07627394494021941,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2547079219800128,
-            "min": 0.251075650769267,
-            "max": 0.36764240514614854,
+            "value": 0.25936860145713364,
+            "min": 0.25927349885380097,
+            "max": 0.36200790193534504,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.20941153796864492,
-            "min": 0.13036264395615194,
-            "max": 0.27689312274257344,
+            "value": 0.20339418860042796,
+            "min": 0.11605569468948115,
+            "max": 0.26271184986712887,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.8376461518745797,
-            "min": 0.5214505758246077,
-            "max": 1.3356465150912604,
+            "value": 0.8135767544017118,
+            "min": 0.4642227787579246,
+            "max": 1.3135592493356443,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 25.204545454545453,
-            "min": 3.659090909090909,
-            "max": 25.204545454545453,
+            "value": 24.818181818181817,
+            "min": 3.477272727272727,
+            "max": 25.09090909090909,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1109.0,
-            "min": 161.0,
-            "max": 1350.0,
+            "value": 1092.0,
+            "min": 153.0,
+            "max": 1371.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 25.204545454545453,
-            "min": 3.659090909090909,
-            "max": 25.204545454545453,
+            "value": 24.818181818181817,
+            "min": 3.477272727272727,
+            "max": 25.09090909090909,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1109.0,
-            "min": 161.0,
-            "max": 1350.0,
+            "value": 1092.0,
+            "min": 153.0,
+            "max": 1371.0,
             "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1701037864",
-        "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=SnowballTarget2 --no-graphics",
+        "start_time_seconds": "1701655278",
+        "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",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.1.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1701038360"
+        "end_time_seconds": "1701655742"
     },
-    "total": 495.43444345699936,
+    "total": 463.6502280390001,
     "count": 1,
-    "self": 0.4246014259988442,
+    "self": 0.6697580100002369,
     "children": {
         "run_training.setup": {
-            "total": 0.08586486000012883,
+            "total": 0.07771567899999354,
             "count": 1,
-            "self": 0.08586486000012883
+            "self": 0.07771567899999354
         },
         "TrainerController.start_learning": {
-            "total": 494.9239771710004,
+            "total": 462.9027543499999,
             "count": 1,
-            "self": 0.606251619924933,
+            "self": 0.518994786000917,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.1704131740002595,
+                    "total": 3.4131496290000314,
                     "count": 1,
-                    "self": 4.1704131740002595
+                    "self": 3.4131496290000314
                 },
                 "TrainerController.advance": {
-                    "total": 490.0612222990753,
-                    "count": 18202,
-                    "self": 0.27690172708707905,
+                    "total": 458.884180524999,
+                    "count": 18201,
+                    "self": 0.24944113998787998,
                     "children": {
                         "env_step": {
-                            "total": 489.78432057198825,
-                            "count": 18202,
-                            "self": 334.32922170503434,
+                            "total": 458.63473938501113,
+                            "count": 18201,
+                            "self": 310.7679812750175,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 155.15922617904243,
-                                    "count": 18202,
-                                    "self": 1.5030841250522826,
+                                    "total": 147.59826931899988,
+                                    "count": 18201,
+                                    "self": 1.402091322000956,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 153.65614205399015,
-                                            "count": 18202,
-                                            "self": 153.65614205399015
+                                            "total": 146.19617799699893,
+                                            "count": 18201,
+                                            "self": 146.19617799699893
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.29587268791146926,
-                                    "count": 18202,
+                                    "total": 0.2684887909937288,
+                                    "count": 18201,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 493.62443401508654,
-                                            "count": 18202,
+                                            "total": 461.67263348701874,
+                                            "count": 18201,
                                             "is_parallel": true,
-                                            "self": 243.9692410680509,
+                                            "self": 228.5188735730129,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002846171000328468,
+                                                            "total": 0.005968991000031565,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006944590008970408,
+                                                            "self": 0.004468811000037931,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.002151711999431427,
+                                                                    "total": 0.0015001799999936338,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.002151711999431427
+                                                                    "self": 0.0015001799999936338
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05210807499997827,
+                                                            "total": 0.046656702999939625,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006189040000208479,
+                                                            "self": 0.0006491869999081246,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00042982900004062685,
+                                                                    "total": 0.0003711240000257021,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00042982900004062685
+                                                                    "self": 0.0003711240000257021
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04923358699988967,
+                                                                    "total": 0.043628388000001905,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04923358699988967
+                                                                    "self": 0.043628388000001905
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018257550000271294,
+                                                                    "total": 0.0020080040000038935,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000371054000879667,
+                                                                    "self": 0.00036630499982948095,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014547009991474624,
+                                                                            "total": 0.0016416990001744125,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014547009991474624
+                                                                            "self": 0.0016416990001744125
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 249.65519294703563,
-                                                    "count": 18201,
+                                                    "total": 233.15375991400583,
+                                                    "count": 18200,
                                                     "is_parallel": true,
-                                                    "self": 10.752482843070993,
+                                                    "self": 10.542252505960732,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.48046503593423,
-                                                            "count": 18201,
+                                                            "total": 5.23215092203111,
+                                                            "count": 18200,
                                                             "is_parallel": true,
-                                                            "self": 5.48046503593423
+                                                            "self": 5.23215092203111
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 198.7942765460698,
-                                                            "count": 18201,
+                                                            "total": 184.41406990400242,
+                                                            "count": 18200,
                                                             "is_parallel": true,
-                                                            "self": 198.7942765460698
+                                                            "self": 184.41406990400242
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 34.62796852196061,
-                                                            "count": 18201,
+                                                            "total": 32.96528658201157,
+                                                            "count": 18200,
                                                             "is_parallel": true,
-                                                            "self": 6.636805659996298,
+                                                            "self": 6.181303478054133,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 27.991162861964312,
-                                                                    "count": 182010,
+                                                                    "total": 26.78398310395744,
+                                                                    "count": 182000,
                                                                     "is_parallel": true,
-                                                                    "self": 27.991162861964312
+                                                                    "self": 26.78398310395744
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.00016092999976535793,
+                    "total": 0.00011420900000302936,
                     "count": 1,
-                    "self": 0.00016092999976535793,
+                    "self": 0.00011420900000302936,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 485.76029818302277,
-                                    "count": 521151,
+                                    "total": 454.9316594960094,
+                                    "count": 492050,
                                     "is_parallel": true,
-                                    "self": 11.475574856720868,
+                                    "self": 10.534527471932051,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 273.56407442129967,
-                                            "count": 521151,
+                                            "total": 257.5263902000777,
+                                            "count": 492050,
                                             "is_parallel": true,
-                                            "self": 273.0222539102997,
+                                            "self": 256.5625163030775,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 0.541820510999969,
+                                                    "total": 0.9638738970002123,
                                                     "count": 4,
                                                     "is_parallel": true,
-                                                    "self": 0.541820510999969
+                                                    "self": 0.9638738970002123
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 200.72064890500224,
+                                            "total": 186.87074182399965,
                                             "count": 90,
                                             "is_parallel": true,
-                                            "self": 68.06261840599745,
+                                            "self": 57.56150328500212,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 132.65803049900478,
+                                                    "total": 129.30923853899753,
                                                     "count": 4587,
                                                     "is_parallel": true,
-                                                    "self": 132.65803049900478
+                                                    "self": 129.30923853899753
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08592914800010476,
+                    "total": 0.08631520099993395,
                     "count": 1,
-                    "self": 0.0009161380003206432,
+                    "self": 0.0009646979999615724,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08501300999978412,
+                            "total": 0.08535050299997238,
                             "count": 1,
-                            "self": 0.08501300999978412
+                            "self": 0.08535050299997238
                         }
                     }
                 }

run_logs/training_status.json

@@ -3,57 +3,57 @@
         "checkpoints": [
             {
                 "steps": 49936,
-                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 12.909090909090908,
-                "creation_time": 1701037996.5639346,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 13.545454545454545,
+                "creation_time": 1701655398.9127426,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             },
             {
                 "steps": 99960,
-                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 21.09090909090909,
-                "creation_time": 1701038118.6184068,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 21.90909090909091,
+                "creation_time": 1701655516.6598365,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
                 ]
             },
             {
                 "steps": 149984,
-                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 24.0,
-                "creation_time": 1701038240.1301637,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 24.363636363636363,
+                "creation_time": 1701655628.885201,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
                 ]
             },
             {
                 "steps": 199984,
-                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 26.181818181818183,
-                "creation_time": 1701038359.5553951,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 24.818181818181817,
+                "creation_time": 1701655741.5178356,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
-                "steps": 200200,
-                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200200.onnx",
-                "reward": 25.272727272727273,
-                "creation_time": 1701038359.68996,
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 24.818181818181817,
+                "creation_time": 1701655741.6299782,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-200200.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200200,
-            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
-            "reward": 25.272727272727273,
-            "creation_time": 1701038359.68996,
+            "steps": 200112,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 24.818181818181817,
+            "creation_time": 1701655741.6299782,
             "auxillary_file_paths": [
-                "results/SnowballTarget2/SnowballTarget/SnowballTarget-200200.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },