First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ca4680f189b5d27ad076d55f6ba344bd5f33f2fc1069fd3f7886dd0fe3fd6a2
+oid sha256:211c2c43680cf69bcc9c37ad0dc68afb2ec1ef96c18a4f1bbcd45966683aaf08
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0175f0b85440c73ece9cca9d0eca53b2af34e419230739bae950afecfe3b34b6
+oid sha256:f87dbbaaeeb2a07ef94b0d7c1f53a6cf75539be67ebba11b1f43d01d90aaf3f9
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c98b306c782e9893a00a2087561c3b9636136f7d5ff8389d9fa58f4a556640ad
+oid sha256:2e30ceacd54628134e79c16872610a4d7b82a20dc42d0f9c775ef23a6fd5fdcc
 size 3849604

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ca4680f189b5d27ad076d55f6ba344bd5f33f2fc1069fd3f7886dd0fe3fd6a2
+oid sha256:211c2c43680cf69bcc9c37ad0dc68afb2ec1ef96c18a4f1bbcd45966683aaf08
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a067fc98144e57fdfbade2f3465f3cdc56be969515e7c9d76af5c6cbeeed9ee5
+oid sha256:9edd0153dc1ab05854926b0f01c753a2e3a31f24b7b5153ed7d1fb89e6c000b7
 size 3849604

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ca4680f189b5d27ad076d55f6ba344bd5f33f2fc1069fd3f7886dd0fe3fd6a2
+oid sha256:211c2c43680cf69bcc9c37ad0dc68afb2ec1ef96c18a4f1bbcd45966683aaf08
 size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63e6af590a62a8f21787ef5df3d61c4d564ae0d2573a8cdf2c041603bb216c5b
+oid sha256:a5edb287bd5be607a75c999e722c800c02da760f2cca6991fcdfdf707729fa40
 size 3849604

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2a2c4e74fe0bf0e2911ea98ec31da1a14233ecc5b1cfa147d43f3ba587553fa
+oid sha256:2f43a15b091e851cbbfb65b6f0af06552ddf39ab50d7651fba7a578aa3616217
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe95be55d3667c0c3b46325278baa98cf9442d9cc54370cf49e85c825b2e461b
+oid sha256:1c2e3f4ec3b89d9cfb631f4fe40a550617bd7131287b7ac43eec7a86868bbb98
 size 3849527

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e5589987a75d0926416772b124253824f283f1ce96cd80480b94dea97985d5e
+oid sha256:526ab80576a46df82bf1cb601f26398be9b11caeae0d87d1dc45a2205215f8ce
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1fd9d6910e5720343caab15eeea3f2a1a2ca9aba5bb0922d51e2a9eaddf2948
+oid sha256:1ae6006d1c29b003c2fc1193d947e26c17a030e093e552d08837277366972670
 size 3849527

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27c7ede1b36495032bef11211bbeca648f606766fd8406639664ea07742497c1
+oid sha256:b5f4749589b52da21178083bdcba69b44505192e7b5bdf0608e5ad704ac1bd0a
 size 3848757

SnowballTarget/events.out.tfevents.1760345391.9e633f17ba3b.13091.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aa46d45ea8243e83381fea9806333a6a75184c13beb62e4ef997873de45c185
+size 23234

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.001, "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}

configuration.yaml

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
-      learning_rate: 0.0003
+      learning_rate: 0.001
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95

run_logs/Player-0.log

@@ -34,7 +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  0.207 seconds
+- Completed reload, in  0.134 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 +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: 0.756845 ms
+UnloadTime: 1.037119 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 +178,13 @@ Memory Statistics:
       Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 7.3 MB
+      Peak Allocated memory 7.1 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 17.2 MB
+      Peak Allocated memory 17.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -213,7 +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]: 3566 frames, [64.0 KB-128.0 KB]: 1892 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4919 frames, [64.0 KB-128.0 KB]: 539 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.3 KB

run_logs/timers.json

@@ -2,15 +2,15 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.985091507434845,
-            "min": 0.985091507434845,
-            "max": 2.8507564067840576,
+            "value": 0.8951362371444702,
+            "min": 0.8951362371444702,
+            "max": 2.8421597480773926,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 9362.3095703125,
-            "min": 9362.3095703125,
-            "max": 29100.521484375,
+            "value": 8507.375,
+            "min": 8507.375,
+            "max": 29012.765625,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
@@ -26,51 +26,51 @@
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 11.93070125579834,
-            "min": 0.47702160477638245,
-            "max": 11.93070125579834,
+            "value": 13.402416229248047,
+            "min": 0.38161036372184753,
+            "max": 13.418840408325195,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2326.48681640625,
-            "min": 92.54219055175781,
-            "max": 2423.24560546875,
+            "value": 2613.47119140625,
+            "min": 74.03240966796875,
+            "max": 2738.68798828125,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06536815873565216,
-            "min": 0.06027207487855134,
-            "max": 0.07478094003996447,
+            "value": 0.07083638905839738,
+            "min": 0.06340313001333818,
+            "max": 0.07508575118223307,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.26147263494260864,
-            "min": 0.25677855424446,
-            "max": 0.35465437079020534,
+            "value": 0.28334555623358954,
+            "min": 0.2536125200533527,
+            "max": 0.3754287559111653,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.18724291209204524,
-            "min": 0.11755183423234736,
-            "max": 0.2609259683711856,
+            "value": 0.20727687277922444,
+            "min": 0.13452830472755628,
+            "max": 0.2705845713615418,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.748971648368181,
-            "min": 0.47020733692938943,
-            "max": 1.304629841855928,
+            "value": 0.8291074911168977,
+            "min": 0.5381132189102251,
+            "max": 1.352922856807709,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
+            "value": 2.6940097306000015e-05,
+            "min": 2.6940097306000015e-05,
+            "max": 0.000972940002706,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
+            "value": 0.00010776038922400006,
+            "min": 0.00010776038922400006,
+            "max": 0.004617200038280001,
             "count": 20
         },
         "SnowballTarget.Policy.Epsilon.mean": {
@@ -110,27 +110,27 @@
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 23.704545454545453,
-            "min": 3.772727272727273,
-            "max": 23.704545454545453,
+            "value": 25.84090909090909,
+            "min": 3.75,
+            "max": 26.563636363636363,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1043.0,
-            "min": 166.0,
-            "max": 1290.0,
+            "value": 1137.0,
+            "min": 165.0,
+            "max": 1461.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 23.704545454545453,
-            "min": 3.772727272727273,
-            "max": 23.704545454545453,
+            "value": 25.84090909090909,
+            "min": 3.75,
+            "max": 26.563636363636363,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1043.0,
-            "min": 166.0,
-            "max": 1290.0,
+            "value": 1137.0,
+            "min": 165.0,
+            "max": 1461.0,
             "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1760336993",
+        "start_time_seconds": "1760345390",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "ml-agents/mlagents/trainers/learn.py ./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=SnowballTarget1 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1760337539"
+        "end_time_seconds": "1760345965"
     },
-    "total": 546.4406419390001,
+    "total": 575.2420856549998,
     "count": 1,
-    "self": 1.2085737080002446,
+    "self": 0.5422745800001394,
     "children": {
         "run_training.setup": {
-            "total": 0.033580171999915365,
+            "total": 0.03296162899960109,
             "count": 1,
-            "self": 0.033580171999915365
+            "self": 0.03296162899960109
         },
         "TrainerController.start_learning": {
-            "total": 545.1984880589999,
+            "total": 574.666849446,
             "count": 1,
-            "self": 0.5886274569983243,
+            "self": 0.5943243419860664,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.921782846000042,
+                    "total": 3.5378566899998987,
                     "count": 1,
-                    "self": 2.921782846000042
+                    "self": 3.5378566899998987
                 },
                 "TrainerController.advance": {
-                    "total": 541.5722603210015,
+                    "total": 570.4634562110141,
                     "count": 18192,
-                    "self": 0.5858174380146011,
+                    "self": 0.65283802996737,
                     "children": {
                         "env_step": {
-                            "total": 391.878538777994,
+                            "total": 406.7492258800112,
                             "count": 18192,
-                            "self": 340.2655915360143,
+                            "self": 354.2378033169716,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 51.25814986999694,
+                                    "total": 52.145517521032616,
                                     "count": 18192,
-                                    "self": 1.7320374219995074,
+                                    "self": 1.8744545710715101,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 49.526112447997434,
+                                            "total": 50.271062949961106,
                                             "count": 18192,
-                                            "self": 49.526112447997434
+                                            "self": 50.271062949961106
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.3547973719827269,
+                                    "total": 0.3659050420069434,
                                     "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 542.5070456669833,
+                                            "total": 571.7298795600573,
                                             "count": 18192,
                                             "is_parallel": true,
-                                            "self": 246.22527346800257,
+                                            "self": 264.6254941160414,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.004903775999991922,
+                                                            "total": 0.007113356999980169,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0033635200003345744,
+                                                            "self": 0.004611848999047652,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0015402559996573473,
+                                                                    "total": 0.0025015080009325175,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0015402559996573473
+                                                                    "self": 0.0025015080009325175
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.0407911330000843,
+                                                            "total": 0.042860598000061145,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006536550000646457,
+                                                            "self": 0.0007444420002684637,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00044302799994966335,
+                                                                    "total": 0.0004822060000151396,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00044302799994966335
+                                                                    "self": 0.0004822060000151396
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.037540294999985235,
+                                                                    "total": 0.039151152999693295,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.037540294999985235
+                                                                    "self": 0.039151152999693295
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0021541550000847565,
+                                                                    "total": 0.002482797000084247,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000433691999887742,
+                                                                    "self": 0.0004883100004917651,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0017204630001970145,
+                                                                            "total": 0.001994486999592482,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0017204630001970145
+                                                                            "self": 0.001994486999592482
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 296.2817721989808,
+                                                    "total": 307.10438544401586,
                                                     "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 13.206685173977803,
+                                                    "self": 14.31028785004628,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 6.934236021999368,
+                                                            "total": 7.436327548994541,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 6.934236021999368
+                                                            "self": 7.436327548994541
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 229.25232487100902,
+                                                            "total": 237.33834766901646,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 229.25232487100902
+                                                            "self": 237.33834766901646
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 46.88852613199458,
+                                                            "total": 48.019422375958584,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 8.258315647952486,
+                                                            "self": 8.510028044971477,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 38.630210484042095,
+                                                                    "total": 39.50939433098711,
                                                                     "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 38.630210484042095
+                                                                    "self": 39.50939433098711
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 149.10790410499294,
+                            "total": 163.06139230103554,
                             "count": 18192,
-                            "self": 0.7252828829826967,
+                            "self": 0.7612348949978696,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 28.45353181001019,
+                                    "total": 29.261816046036984,
                                     "count": 18192,
-                                    "self": 28.03547967201007,
+                                    "self": 28.88918513303679,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.418052138000121,
+                                            "total": 0.3726309130001937,
                                             "count": 4,
-                                            "self": 0.418052138000121
+                                            "self": 0.3726309130001937
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 119.92908941200005,
+                                    "total": 133.0383413600007,
                                     "count": 90,
-                                    "self": 47.10123283199641,
+                                    "self": 49.51847884300014,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 72.82785658000364,
+                                            "total": 83.51986251700055,
                                             "count": 4587,
-                                            "self": 72.82785658000364
+                                            "self": 83.51986251700055
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.4859999737382168e-06,
+                    "total": 1.094000253942795e-06,
                     "count": 1,
-                    "self": 1.4859999737382168e-06
+                    "self": 1.094000253942795e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.11581594900007985,
+                    "total": 0.07121110899970517,
                     "count": 1,
-                    "self": 0.0011478690000785718,
+                    "self": 0.0009590009995008586,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.11466808000000128,
+                            "total": 0.07025210800020432,
                             "count": 1,
-                            "self": 0.11466808000000128
+                            "self": 0.07025210800020432
                         }
                     }
                 }

run_logs/training_status.json

@@ -4,8 +4,8 @@
             {
                 "steps": 49936,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 14.454545454545455,
-                "creation_time": 1760337128.5465505,
+                "reward": 15.909090909090908,
+                "creation_time": 1760345530.8348508,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
                 ]
@@ -13,8 +13,8 @@
             {
                 "steps": 99960,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 19.636363636363637,
-                "creation_time": 1760337264.3383148,
+                "reward": 24.454545454545453,
+                "creation_time": 1760345681.327484,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
                 ]
@@ -22,8 +22,8 @@
             {
                 "steps": 149984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 23.0,
-                "creation_time": 1760337406.6120768,
+                "reward": 26.454545454545453,
+                "creation_time": 1760345823.6489224,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
                 ]
@@ -31,8 +31,8 @@
             {
                 "steps": 199984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 23.727272727272727,
-                "creation_time": 1760337538.3609374,
+                "reward": 25.454545454545453,
+                "creation_time": 1760345965.2895772,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
@@ -40,8 +40,8 @@
             {
                 "steps": 200112,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 23.727272727272727,
-                "creation_time": 1760337538.5015504,
+                "reward": 25.454545454545453,
+                "creation_time": 1760345965.3736358,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
@@ -50,8 +50,8 @@
         "final_checkpoint": {
             "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 23.727272727272727,
-            "creation_time": 1760337538.5015504,
+            "reward": 25.454545454545453,
+            "creation_time": 1760345965.3736358,
             "auxillary_file_paths": [
                 "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]