Second Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a585090a8068402976a42ab4621ed41d437644a7ebc9347e26a8e681980c8f
+oid sha256:68464642da5fe7eef5742a830e7e3507de4c499c8e70ea85f8cdd9822b2ce1ba
 size 59101

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31dc64530bc24ef98184c1a671e319ce1d157d6a666dc6892e1de1998ec34bac
+oid sha256:8dedb8bef27a25185ef7f071667641e42bde5cc7f112d5c1c691e78ca002e9d5
 size 59101

SnowballTarget/SnowballTarget-149984.onnx.data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddfdbe67c1130e294982789dad9e88023d4a293ce0e51893e5d4a9bcee719b3d
+oid sha256:2f38332c303b6cad4fe32719708b0f6b830efbc524e0fcbecfd56e2f67a2f809
 size 641024

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0fd353294214df8850689e82f1222f9d453381897c602f0ac279dbc8721d39
+oid sha256:1fa5e0f4930d699ddbd308656747e89784436d2e7992193a2fcf448b4ae7a11f
 size 3850564

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c21b98f4ddd9caf57a0d517863135d393495ed3c76c558e2b9955f0a044f6fb3
+oid sha256:facc1af6131d2809403ce7d669f560cd76bbf869a26c8e94f0b52cf71eca4cf3
 size 59101

SnowballTarget/SnowballTarget-199984.onnx.data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a070fe3121ac6d12cc03282c1d2a625a2d7fa7d96fca3adbd6d3e564d19dee
+oid sha256:26ac39d6609960e39601259d8033bdef89a1040423feebc090031a046a35f73c
 size 641024

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d1029b3c400235c56d3a1386e7ddacad631d8335d824ad96f42e0c80f0da9aa
+oid sha256:a42bdff68dcd232ffbdac95606031dc1b9c430b91ac7044b1a8d0719404204bb
 size 3850564

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a585090a8068402976a42ab4621ed41d437644a7ebc9347e26a8e681980c8f
+oid sha256:68464642da5fe7eef5742a830e7e3507de4c499c8e70ea85f8cdd9822b2ce1ba
 size 59101

SnowballTarget/SnowballTarget-200112.onnx.data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a070fe3121ac6d12cc03282c1d2a625a2d7fa7d96fca3adbd6d3e564d19dee
+oid sha256:26ac39d6609960e39601259d8033bdef89a1040423feebc090031a046a35f73c
 size 641024

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eb3a2a7d6da6c91766b2216aac598cce61aa8386340adaaea7412880d1889b6
+oid sha256:14713ee1ea1399377077501921d8c0a4c66e468709991e95cf5afd3c1f255144
 size 3850564

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0479868ebbdfca549bb87db17c10c0428460b3a3e42123b2b2f72726e8d859aa
+oid sha256:5d0b70f904cff800b4a049702dca142f9aeb36ea917868d68d20e85f6fa526f9
 size 59094

SnowballTarget/SnowballTarget-49936.onnx.data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a86c614392d24d2c30403841da8c4d5516385c35641ae1767563c373253ae392
+oid sha256:875aa267375dee58eb965fa25976cbe016c6625e8e5dbe1b550123af426395de
 size 641024

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:747f2cefbb6608101e99e20c478e292c16767cce97b3f44b422a0eb197ed025e
+oid sha256:250be8cadc0bffb9c5ed5689088f1e4631c2ca5f0c85b6f393111b7b7e89cead
 size 3850487

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c87e8d93b05b1b9b2ec2e00687e52db5be61f68975c729466ddcb0241970005
+oid sha256:1269d4160f3ac5eb296e2d0be3918441c55aac2760734bc9ea7d1e8f786d41cf
 size 59094

SnowballTarget/SnowballTarget-99960.onnx.data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:701576c7f43b2b7eb310e79b012c0eebc06d042f22e331e897732a8d53359cca
+oid sha256:dfa4bb8dff48377cef84e2b8fe80b19499aac74f23e0f3ae99f41eed115d4db6
 size 641024

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4a8bbdbf0180415e15ca849e09674edb801266c61816fb9f65f5e43284a16d6
+oid sha256:e5a1b2f440f5b42b8c12f4d7068fd2a5918bcb5ef7b173c300c0393019c180b0
 size 3850487

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b813d130a02d8ff01ed70a7a37b918e9b12ef6c25dd23c3b226c998929a9c188
+oid sha256:c2a268999a3264684a575836eda6790a9639c488a3667ef1ee4773b119e9cce8
 size 3849717

SnowballTarget/events.out.tfevents.1769891503.796f8044c23d.11009.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2039d34965624ca7758e096e36bc0422327e1f1e1713b046ee4ab97ea9f1f94b
+size 23783

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0005, "beta": 0.005, "epsilon": 0.2, "lambd": 0.93, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -5,10 +5,10 @@ behaviors:
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
-      learning_rate: 0.0005
+      learning_rate: 0.0003
       beta: 0.005
       epsilon: 0.2
-      lambd: 0.93
+      lambd: 0.95
       num_epoch: 3
       shared_critic: false
       learning_rate_schedule: linear

run_logs/Player-0.log

@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.082 seconds
+- Completed reload, in  0.079 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 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.623280 ms
+UnloadTime: 0.597635 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 +166,7 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 41
+  Peak main deferred allocation count 44
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
@@ -181,7 +181,7 @@ Memory Statistics:
       Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.2 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
@@ -210,10 +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]: 4549 frames, [64.0 KB-128.0 KB]: 909 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 2447 frames, [64.0 KB-128.0 KB]: 3011 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 67.3 KB
+      Peak Allocated memory 68.2 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": 0.8425711393356323,
-            "min": 0.8425711393356323,
-            "max": 2.8333139419555664,
+            "value": 1.1120237112045288,
+            "min": 1.0221964120864868,
+            "max": 2.8125956058502197,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8007.7958984375,
-            "min": 8007.7958984375,
-            "max": 28922.46875,
+            "value": 10568.673828125,
+            "min": 10434.5810546875,
+            "max": 28710.9765625,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
@@ -26,51 +26,51 @@
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 13.22083854675293,
-            "min": 0.3146674931049347,
-            "max": 13.22083854675293,
+            "value": 10.936310768127441,
+            "min": 0.24286645650863647,
+            "max": 10.936310768127441,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2578.0634765625,
-            "min": 61.045494079589844,
-            "max": 2676.705078125,
+            "value": 2132.58056640625,
+            "min": 47.116092681884766,
+            "max": 2226.1708984375,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06352646306029283,
-            "min": 0.06027381585473075,
-            "max": 0.07400025115508185,
+            "value": 0.07260002126214185,
+            "min": 0.06467748650906216,
+            "max": 0.07374800986464262,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2541058522411713,
-            "min": 0.241095263418923,
-            "max": 0.37000125577540927,
+            "value": 0.2904000850485674,
+            "min": 0.25870994603624864,
+            "max": 0.36874004932321314,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.14947438521274165,
-            "min": 0.10749810681034647,
-            "max": 0.20987866953307507,
+            "value": 0.18903927512320817,
+            "min": 0.14099524074517117,
+            "max": 0.2730388129458708,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.5978975408509666,
-            "min": 0.42999242724138587,
-            "max": 1.0493933476653754,
+            "value": 0.7561571004928327,
+            "min": 0.5639809629806847,
+            "max": 1.365194064729354,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 1.347009730600001e-05,
-            "min": 1.347009730600001e-05,
-            "max": 0.00048647000270600005,
+            "value": 8.082097306000005e-06,
+            "min": 8.082097306000005e-06,
+            "max": 0.000291882002706,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 5.388038922400004e-05,
-            "min": 5.388038922400004e-05,
-            "max": 0.00230860003828,
+            "value": 3.232838922400002e-05,
+            "min": 3.232838922400002e-05,
+            "max": 0.00138516003828,
             "count": 20
         },
         "SnowballTarget.Policy.Epsilon.mean": {
@@ -110,27 +110,27 @@
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 26.0,
-            "min": 4.204545454545454,
-            "max": 26.21818181818182,
+            "value": 21.636363636363637,
+            "min": 3.772727272727273,
+            "max": 21.636363636363637,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1144.0,
-            "min": 185.0,
-            "max": 1442.0,
+            "value": 952.0,
+            "min": 166.0,
+            "max": 1178.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 26.0,
-            "min": 4.204545454545454,
-            "max": 26.21818181818182,
+            "value": 21.636363636363637,
+            "min": 3.772727272727273,
+            "max": 21.636363636363637,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1144.0,
-            "min": 185.0,
-            "max": 1442.0,
+            "value": 952.0,
+            "min": 166.0,
+            "max": 1178.0,
             "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,7 +148,7 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1769890843",
+        "start_time_seconds": "1769891502",
         "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 --force",
         "mlagents_version": "1.2.0.dev0",
@@ -156,59 +156,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.10.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1769891283"
+        "end_time_seconds": "1769891938"
     },
-    "total": 440.85665778399994,
+    "total": 435.53454671300005,
     "count": 1,
-    "self": 0.37775079099969844,
+    "self": 0.4280878899999152,
     "children": {
         "run_training.setup": {
-            "total": 0.023213248000047315,
+            "total": 0.024383125999975164,
             "count": 1,
-            "self": 0.023213248000047315
+            "self": 0.024383125999975164
         },
         "TrainerController.start_learning": {
-            "total": 440.4556937450002,
+            "total": 435.08207569700016,
             "count": 1,
-            "self": 0.347771616018008,
+            "self": 0.33599969897522897,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.7065193939999972,
+                    "total": 2.1866478430001735,
                     "count": 1,
-                    "self": 1.7065193939999972
+                    "self": 2.1866478430001735
                 },
                 "TrainerController.advance": {
-                    "total": 436.51373562398203,
+                    "total": 430.6947136500248,
                     "count": 18192,
-                    "self": 0.36601350497903695,
+                    "self": 0.3362591200602765,
                     "children": {
                         "env_step": {
-                            "total": 310.60210236301145,
+                            "total": 305.69837874198356,
                             "count": 18192,
-                            "self": 242.78736893402106,
+                            "self": 239.00231539799324,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 67.59740000899183,
+                                    "total": 66.48070533299415,
                                     "count": 18192,
-                                    "self": 1.2480877779964885,
+                                    "self": 1.2163548089861251,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 66.34931223099534,
+                                            "total": 65.26435052400802,
                                             "count": 18192,
-                                            "self": 66.34931223099534
+                                            "self": 65.26435052400802
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.21733341999856748,
+                                    "total": 0.21535801099616947,
                                     "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 435.04443979898656,
+                                            "total": 428.92654440099705,
                                             "count": 18192,
                                             "is_parallel": true,
-                                            "self": 222.12733008196642,
+                                            "self": 218.68688461299325,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0019342180000876397,
+                                                            "total": 0.0018740169998636702,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006062449999717501,
+                                                            "self": 0.0005569139989347605,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013279730001158896,
+                                                                    "total": 0.0013171030009289098,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013279730001158896
+                                                                    "self": 0.0013171030009289098
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.038514487000156805,
+                                                            "total": 0.07094306299995878,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005723650001527858,
+                                                            "self": 0.0005387800001699361,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00040792499999042775,
+                                                                    "total": 0.0004080789999534318,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00040792499999042775
+                                                                    "self": 0.0004080789999534318
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03576126400002977,
+                                                                    "total": 0.06602191399997537,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03576126400002977
+                                                                    "self": 0.06602191399997537
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017729329999838228,
+                                                                    "total": 0.003974289999860048,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003507460000946594,
+                                                                    "self": 0.0004329550010879757,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014221869998891634,
+                                                                            "total": 0.003541334998772072,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014221869998891634
+                                                                            "self": 0.003541334998772072
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 212.91710971702014,
+                                                    "total": 210.2396597880038,
                                                     "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 10.010626490047798,
+                                                    "self": 9.836912392081103,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.3549900499799605,
+                                                            "total": 5.210151998959191,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 5.3549900499799605
+                                                            "self": 5.210151998959191
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 162.07854989700468,
+                                                            "total": 160.18188624398408,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 162.07854989700468
+                                                            "self": 160.18188624398408
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 35.4729432799877,
+                                                            "total": 35.010709152979416,
                                                             "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 6.561606223994659,
+                                                            "self": 6.368384373154186,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 28.911337055993044,
+                                                                    "total": 28.64232477982523,
                                                                     "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 28.911337055993044
+                                                                    "self": 28.64232477982523
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 125.54561975599154,
+                            "total": 124.66007578798099,
                             "count": 18192,
-                            "self": 0.4526060259602218,
+                            "self": 0.40798532700182477,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 34.467695753031194,
+                                    "total": 35.02175048697973,
                                     "count": 18192,
-                                    "self": 25.64319845003115,
+                                    "self": 25.731180004979706,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 8.824497303000044,
+                                            "total": 9.290570482000021,
                                             "count": 4,
-                                            "self": 8.824497303000044
+                                            "self": 9.290570482000021
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 90.62531797700012,
+                                    "total": 89.23033997399943,
                                     "count": 90,
-                                    "self": 37.09300392998421,
+                                    "self": 36.98271864301296,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 53.532314047015916,
+                                            "total": 52.247621330986476,
                                             "count": 4587,
-                                            "self": 53.532314047015916
+                                            "self": 52.247621330986476
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0560002010606695e-06,
+                    "total": 1.0160001693293452e-06,
                     "count": 1,
-                    "self": 1.0560002010606695e-06
+                    "self": 1.0160001693293452e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 1.8876660549999542,
+                    "total": 1.8647134889997687,
                     "count": 1,
-                    "self": 0.00038585299989790656,
+                    "self": 0.00045965299977979157,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 1.8872802020000563,
+                            "total": 1.864253835999989,
                             "count": 1,
-                            "self": 1.8872802020000563
+                            "self": 1.864253835999989
                         }
                     }
                 }

run_logs/training_status.json

@@ -4,8 +4,8 @@
             {
                 "steps": 49936,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 16.363636363636363,
-                "creation_time": 1769890954.3274972,
+                "reward": 13.181818181818182,
+                "creation_time": 1769891612.1475348,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
                 ]
@@ -13,8 +13,8 @@
             {
                 "steps": 99960,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 21.0,
-                "creation_time": 1769891063.575847,
+                "reward": 15.909090909090908,
+                "creation_time": 1769891718.7945433,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
                 ]
@@ -22,8 +22,8 @@
             {
                 "steps": 149984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 25.727272727272727,
-                "creation_time": 1769891172.874066,
+                "reward": 21.545454545454547,
+                "creation_time": 1769891826.9017894,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
                 ]
@@ -31,8 +31,8 @@
             {
                 "steps": 199984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.454545454545453,
-                "creation_time": 1769891281.5870855,
+                "reward": 21.636363636363637,
+                "creation_time": 1769891935.8171434,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
@@ -40,8 +40,8 @@
             {
                 "steps": 200112,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.454545454545453,
-                "creation_time": 1769891283.4867144,
+                "reward": 21.636363636363637,
+                "creation_time": 1769891937.6938882,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
@@ -50,8 +50,8 @@
         "final_checkpoint": {
             "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 25.454545454545453,
-            "creation_time": 1769891283.4867144,
+            "reward": 21.636363636363637,
+            "creation_time": 1769891937.6938882,
             "auxillary_file_paths": [
                 "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]