Second Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:211c2c43680cf69bcc9c37ad0dc68afb2ec1ef96c18a4f1bbcd45966683aaf08
+oid sha256:61f7338cb947cd8059b48ed8e3c2a75b7585c7270bf904eba07b20296c80c531
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f87dbbaaeeb2a07ef94b0d7c1f53a6cf75539be67ebba11b1f43d01d90aaf3f9
+oid sha256:dbc2e1f80f34d3690a009763fc8f3fdabad23a10b93259839565ec5242c6639f
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e30ceacd54628134e79c16872610a4d7b82a20dc42d0f9c775ef23a6fd5fdcc
+oid sha256:7a7b5333ec745be440db9a1d5aefd82701f2405bfe1730c072c8ad1689b61361
 size 3849604

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:211c2c43680cf69bcc9c37ad0dc68afb2ec1ef96c18a4f1bbcd45966683aaf08
+oid sha256:61f7338cb947cd8059b48ed8e3c2a75b7585c7270bf904eba07b20296c80c531
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9edd0153dc1ab05854926b0f01c753a2e3a31f24b7b5153ed7d1fb89e6c000b7
+oid sha256:ba11c9a1218f4f939c02a66c442cf517e6e637c2414b715f39d606b426fac5ab
 size 3849604

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:211c2c43680cf69bcc9c37ad0dc68afb2ec1ef96c18a4f1bbcd45966683aaf08
+oid sha256:61f7338cb947cd8059b48ed8e3c2a75b7585c7270bf904eba07b20296c80c531
 size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5edb287bd5be607a75c999e722c800c02da760f2cca6991fcdfdf707729fa40
+oid sha256:87845993b78ff214e3e786e42051219f10b3af112c914277687853fe1a8adaa0
 size 3849604

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f43a15b091e851cbbfb65b6f0af06552ddf39ab50d7651fba7a578aa3616217
+oid sha256:4fff8feefbfb3e5b78ef8d3d3f1bf11cc04b7b8274a213a8017989dab9d94d45
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2e3f4ec3b89d9cfb631f4fe40a550617bd7131287b7ac43eec7a86868bbb98
+oid sha256:d768730c7b6832f0823171bf9501535c3525213c98947e5dabf1621c033ffa34
 size 3849527

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:526ab80576a46df82bf1cb601f26398be9b11caeae0d87d1dc45a2205215f8ce
+oid sha256:b8e75822a6b2ef241e785f1016fb0509494e9ec9b1f972907815fccdabbc1111
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ae6006d1c29b003c2fc1193d947e26c17a030e093e552d08837277366972670
+oid sha256:c6dfb67defc66d432a51dde0110663e036b551e5f1513bb02c2cf4b2daf7e851
 size 3849527

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5f4749589b52da21178083bdcba69b44505192e7b5bdf0608e5ad704ac1bd0a
+oid sha256:45c6348dea97795f3dae52a90302e14dec9acea480df54f1c29e587725de1db7
 size 3848757

SnowballTarget/events.out.tfevents.1760348877.9e633f17ba3b.27077.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1122044aef496f757ca4dc60087d1db799cc915185a76a107e5a98b832b06e6
+size 23252

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.001, "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": 0.001, "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": 0.999, "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": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -25,7 +25,7 @@ behaviors:
       deterministic: false
     reward_signals:
       extrinsic:
-        gamma: 0.99
+        gamma: 0.999
         strength: 1.0
         network_settings:
           normalize: false
@@ -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  0.134 seconds
+- Completed reload, in  0.314 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: 1.037119 ms
+UnloadTime: 1.819885 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.
@@ -178,13 +175,13 @@ Memory Statistics:
       Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 7.1 MB
+      Peak Allocated memory 6.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
       Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.3 MB
+      Peak Allocated memory 17.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -213,10 +210,10 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4919 frames, [64.0 KB-128.0 KB]: 539 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5275 frames, [64.0 KB-128.0 KB]: 183 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 67.3 KB
+      Peak Allocated memory 65.8 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
       Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames

run_logs/timers.json

@@ -2,15 +2,15 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.8951362371444702,
-            "min": 0.8951362371444702,
-            "max": 2.8421597480773926,
+            "value": 1.1696356534957886,
+            "min": 1.1586006879806519,
+            "max": 2.8567614555358887,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8507.375,
-            "min": 8507.375,
-            "max": 29012.765625,
+            "value": 11116.216796875,
+            "min": 11116.216796875,
+            "max": 29161.8203125,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
@@ -26,39 +26,39 @@
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 13.402416229248047,
-            "min": 0.38161036372184753,
-            "max": 13.418840408325195,
+            "value": 80.743896484375,
+            "min": 0.37964004278182983,
+            "max": 80.743896484375,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2613.47119140625,
-            "min": 74.03240966796875,
-            "max": 2738.68798828125,
+            "value": 15745.0595703125,
+            "min": 73.6501693725586,
+            "max": 15833.3828125,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07083638905839738,
-            "min": 0.06340313001333818,
-            "max": 0.07508575118223307,
+            "value": 0.06701226236170851,
+            "min": 0.05924823112587796,
+            "max": 0.07278921084590348,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.28334555623358954,
-            "min": 0.2536125200533527,
-            "max": 0.3754287559111653,
+            "value": 0.26804904944683405,
+            "min": 0.2591948176844858,
+            "max": 0.3639460542295174,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.20727687277922444,
-            "min": 0.13452830472755628,
-            "max": 0.2705845713615418,
+            "value": 0.46281355677866465,
+            "min": 0.1529703062614335,
+            "max": 0.6265163567720674,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.8291074911168977,
-            "min": 0.5381132189102251,
-            "max": 1.352922856807709,
+            "value": 1.8512542271146586,
+            "min": 0.611881225045734,
+            "max": 3.132581783860337,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 25.84090909090909,
-            "min": 3.75,
-            "max": 26.563636363636363,
+            "value": 25.636363636363637,
+            "min": 3.4318181818181817,
+            "max": 26.613636363636363,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1137.0,
-            "min": 165.0,
-            "max": 1461.0,
+            "value": 1128.0,
+            "min": 151.0,
+            "max": 1420.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 25.84090909090909,
-            "min": 3.75,
-            "max": 26.563636363636363,
+            "value": 25.636363636363637,
+            "min": 3.4318181818181817,
+            "max": 26.613636363636363,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1137.0,
-            "min": 165.0,
-            "max": 1461.0,
+            "value": 1128.0,
+            "min": 151.0,
+            "max": 1420.0,
             "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1760345390",
+        "start_time_seconds": "1760348875",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "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": "1.2.0.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": "1760345965"
+        "end_time_seconds": "1760349445"
     },
-    "total": 575.2420856549998,
+    "total": 570.327507424,
     "count": 1,
-    "self": 0.5422745800001394,
+    "self": 1.0985130230001232,
     "children": {
         "run_training.setup": {
-            "total": 0.03296162899960109,
+            "total": 0.04536594999990484,
             "count": 1,
-            "self": 0.03296162899960109
+            "self": 0.04536594999990484
         },
         "TrainerController.start_learning": {
-            "total": 574.666849446,
+            "total": 569.183628451,
             "count": 1,
-            "self": 0.5943243419860664,
+            "self": 0.6299554249917492,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.5378566899998987,
+                    "total": 5.05053794899959,
                     "count": 1,
-                    "self": 3.5378566899998987
+                    "self": 5.05053794899959
                 },
                 "TrainerController.advance": {
-                    "total": 570.4634562110141,
+                    "total": 563.3698811720087,
                     "count": 18192,
-                    "self": 0.65283802996737,
+                    "self": 0.6448444780307909,
                     "children": {
                         "env_step": {
-                            "total": 406.7492258800112,
+                            "total": 406.57764273400517,
                             "count": 18192,
-                            "self": 354.2378033169716,
+                            "self": 352.571894519976,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 52.145517521032616,
+                                    "total": 53.61874586097201,
                                     "count": 18192,
-                                    "self": 1.8744545710715101,
+                                    "self": 1.9992169238839779,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 50.271062949961106,
+                                            "total": 51.619528937088035,
                                             "count": 18192,
-                                            "self": 50.271062949961106
+                                            "self": 51.619528937088035
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.3659050420069434,
+                                    "total": 0.3870023530571416,
                                     "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 571.7298795600573,
+                                            "total": 566.2498391761146,
                                             "count": 18192,
                                             "is_parallel": true,
-                                            "self": 264.6254941160414,
+                                            "self": 261.542008055093,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.007113356999980169,
+                                                            "total": 0.00426478200006386,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.004611848999047652,
+                                                            "self": 0.0015539629976046854,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0025015080009325175,
+                                                                    "total": 0.002710819002459175,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0025015080009325175
+                                                                    "self": 0.002710819002459175
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.042860598000061145,
+                                                            "total": 0.04402731299978768,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007444420002684637,
+                                                            "self": 0.0007118049998098286,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004822060000151396,
+                                                                    "total": 0.0004511699999056873,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004822060000151396
+                                                                    "self": 0.0004511699999056873
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.039151152999693295,
+                                                                    "total": 0.04069060400070157,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.039151152999693295
+                                                                    "self": 0.04069060400070157
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002482797000084247,
+                                                                    "total": 0.0021737339993705973,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004883100004917651,
+                                                                    "self": 0.00043069300045317505,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001994486999592482,
+                                                                            "total": 0.0017430409989174223,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001994486999592482
+                                                                            "self": 0.0017430409989174223
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 307.10438544401586,
+                                                    "total": 304.7078311210216,
                                                     "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 14.31028785004628,
+                                                    "self": 13.761532958168573,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 7.436327548994541,
+                                                            "total": 7.448107377951601,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 7.436327548994541
+                                                            "self": 7.448107377951601
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 237.33834766901646,
+                                                            "total": 236.13964651195238,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 237.33834766901646
+                                                            "self": 236.13964651195238
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 48.019422375958584,
+                                                            "total": 47.358544272949075,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 8.510028044971477,
+                                                            "self": 8.386712790981619,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 39.50939433098711,
+                                                                    "total": 38.971831481967456,
                                                                     "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 39.50939433098711
+                                                                    "self": 38.971831481967456
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 163.06139230103554,
+                            "total": 156.14739395997276,
                             "count": 18192,
-                            "self": 0.7612348949978696,
+                            "self": 0.8271200900107942,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 29.261816046036984,
+                                    "total": 30.195439903956867,
                                     "count": 18192,
-                                    "self": 28.88918513303679,
+                                    "self": 29.715409851956792,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.3726309130001937,
+                                            "total": 0.48003005200007465,
                                             "count": 4,
-                                            "self": 0.3726309130001937
+                                            "self": 0.48003005200007465
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 133.0383413600007,
+                                    "total": 125.1248339660051,
                                     "count": 90,
-                                    "self": 49.51847884300014,
+                                    "self": 46.94673122595941,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 83.51986251700055,
+                                            "total": 78.17810274004569,
                                             "count": 4587,
-                                            "self": 83.51986251700055
+                                            "self": 78.17810274004569
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.094000253942795e-06,
+                    "total": 1.7279999156016856e-06,
                     "count": 1,
-                    "self": 1.094000253942795e-06
+                    "self": 1.7279999156016856e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.07121110899970517,
+                    "total": 0.13325217700003122,
                     "count": 1,
-                    "self": 0.0009590009995008586,
+                    "self": 0.0035736320005526068,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.07025210800020432,
+                            "total": 0.12967854499947862,
                             "count": 1,
-                            "self": 0.07025210800020432
+                            "self": 0.12967854499947862
                         }
                     }
                 }

run_logs/training_status.json

@@ -3,57 +3,57 @@
         "checkpoints": [
             {
                 "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 15.909090909090908,
-                "creation_time": 1760345530.8348508,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 16.363636363636363,
+                "creation_time": 1760349020.108223,
                 "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": 24.454545454545453,
-                "creation_time": 1760345681.327484,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 23.363636363636363,
+                "creation_time": 1760349162.1953735,
                 "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": 26.454545454545453,
-                "creation_time": 1760345823.6489224,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 25.09090909090909,
+                "creation_time": 1760349303.0691292,
                 "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": 25.454545454545453,
-                "creation_time": 1760345965.2895772,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.636363636363637,
+                "creation_time": 1760349444.51693,
                 "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": 25.454545454545453,
-                "creation_time": 1760345965.3736358,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 25.636363636363637,
+                "creation_time": 1760349444.668854,
                 "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": 25.454545454545453,
-            "creation_time": 1760345965.3736358,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 25.636363636363637,
+            "creation_time": 1760349444.668854,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },