Second Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3a1a44fd356b0789b0c31e857558c93ec00b2373f9fa5ac4ec93a8621804e9d
+oid sha256:011386b75378b4c1b96c9c92a948a7d3ae7e0d490cb9b900b6ac8c77ed7a17af
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31fd3a906eb00001fefc4ce249acf687e529a951a7ac821ee0b0f9c1a353622f
+oid sha256:ad93abc6559c42308d01bf5427fb8712e5177a3939ab66511faef00b915bbe3b
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a79eb89be2135be095e895034467b646a20742518f4ede133086f2d50abff94c
+oid sha256:794c7562291a6aabcdbddddd9c3a92b8f1ec76e81362e6f3e6948c2cd61682e2
 size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3a1a44fd356b0789b0c31e857558c93ec00b2373f9fa5ac4ec93a8621804e9d
+oid sha256:011386b75378b4c1b96c9c92a948a7d3ae7e0d490cb9b900b6ac8c77ed7a17af
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:014bc7243694e9b6f161a8b22edb3f0889c86870762bbdefdf08785eb2b6c015
+oid sha256:2b7057a9601f8b59b1a8a20f8f3c79dfb1000b1b2cf6099a79760331f6973dab
 size 3850075

SnowballTarget/SnowballTarget-200200.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011386b75378b4c1b96c9c92a948a7d3ae7e0d490cb9b900b6ac8c77ed7a17af
+size 650646

SnowballTarget/SnowballTarget-200200.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61ded5ec2678ba4a5e534dd966c9f734319feaab0eaee44da5342e14d0170582
+size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:055f78a746b54fc2ee8dc218ef16ca75ff3818ae0b091de16c49d059ef2102e1
+oid sha256:c09b14f5c05ef43018deca04dba39b831dea14c3e55a5b6004ff2d92618a3fff
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:119ba902a9e0190ef7a5fdb044754cdd68b07920f808deb8bf9be69fb20f094e
+oid sha256:478d1a2f2f6814ba84987404750045ef3a430300366888e9a2d4ab978ee1345b
 size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8df8e237c4aa7dcd9188e5edcba149d022a7620daac8487b695b1b98a695447
+oid sha256:c95f960feab1d1553489e18739240eb691c6002ce651c738d0127a935d5294d8
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29b033fa96d366afe0b9547f271f587e7ba4e329cd902e337cff1dfd758a6ba7
+oid sha256:199eb9ea2ce3dac030f350e8fec5981966bce635d183689654b78e5eda232bcd
 size 3850000

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0bd44f9149aa5d663c21faff9796cf2e9c097ae19e8c9157b8d78e5181a4f9a
+oid sha256:85bf41a1b006db04de200aca01567410f733c703a59d57aa17c5307ac0405412
 size 3849250

SnowballTarget/events.out.tfevents.1701037865.89016b4c531a.17079.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f63629d1be1e193a13fd758c86e596917bc7739f086102e12e0590ed9bd837
+size 23570

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "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": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -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  0.126 seconds
+- Completed reload, in  0.132 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.961340 ms
+UnloadTime: 0.887110 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]: 5461 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 7.0 MB
+      Peak Allocated memory 6.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
       Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.4 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
@@ -213,7 +210,7 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4650 frames, [64.0 KB-128.0 KB]: 811 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4798 frames, [64.0 KB-128.0 KB]: 663 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 66.8 KB

run_logs/timers.json

@@ -2,15 +2,15 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.8591234683990479,
-            "min": 0.8591234683990479,
-            "max": 2.867922306060791,
+            "value": 0.9833106994628906,
+            "min": 0.9833106994628906,
+            "max": 2.8693156242370605,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8221.8115234375,
-            "min": 8221.8115234375,
-            "max": 29528.126953125,
+            "value": 9410.283203125,
+            "min": 9410.283203125,
+            "max": 29416.22265625,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.983907699584961,
-            "min": 0.41536328196525574,
-            "max": 12.983907699584961,
+            "value": 12.537129402160645,
+            "min": 0.4118865132331848,
+            "max": 12.537129402160645,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2531.862060546875,
-            "min": 80.58047485351562,
-            "max": 2646.513671875,
+            "value": 2444.740234375,
+            "min": 79.9059829711914,
+            "max": 2509.056884765625,
             "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.0742257916672137,
-            "min": 0.06267744534895481,
-            "max": 0.07447498572360287,
+            "value": 0.0636769804950032,
+            "min": 0.06276891269231676,
+            "max": 0.07362485134845152,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2969031666688548,
-            "min": 0.25070978139581923,
-            "max": 0.3723749286180143,
+            "value": 0.2547079219800128,
+            "min": 0.251075650769267,
+            "max": 0.36764240514614854,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.1987991490419589,
-            "min": 0.12892695850300073,
-            "max": 0.2934934151377164,
+            "value": 0.20941153796864492,
+            "min": 0.13036264395615194,
+            "max": 0.27689312274257344,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7951965961678356,
-            "min": 0.5157078340120029,
-            "max": 1.3077987353591358,
+            "value": 0.8376461518745797,
+            "min": 0.5214505758246077,
+            "max": 1.3356465150912604,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 25.5,
-            "min": 3.6136363636363638,
-            "max": 25.636363636363637,
+            "value": 25.204545454545453,
+            "min": 3.659090909090909,
+            "max": 25.204545454545453,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1122.0,
-            "min": 159.0,
-            "max": 1410.0,
+            "value": 1109.0,
+            "min": 161.0,
+            "max": 1350.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 25.5,
-            "min": 3.6136363636363638,
-            "max": 25.636363636363637,
+            "value": 25.204545454545453,
+            "min": 3.659090909090909,
+            "max": 25.204545454545453,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1122.0,
-            "min": 159.0,
-            "max": 1410.0,
+            "value": 1109.0,
+            "min": 161.0,
+            "max": 1350.0,
             "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1701036451",
+        "start_time_seconds": "1701037864",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.1.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1701036954"
+        "end_time_seconds": "1701038360"
     },
-    "total": 502.65913672099987,
+    "total": 495.43444345699936,
     "count": 1,
-    "self": 0.4375511599996571,
+    "self": 0.4246014259988442,
     "children": {
         "run_training.setup": {
-            "total": 0.09002734400019108,
+            "total": 0.08586486000012883,
             "count": 1,
-            "self": 0.09002734400019108
+            "self": 0.08586486000012883
         },
         "TrainerController.start_learning": {
-            "total": 502.131558217,
+            "total": 494.9239771710004,
             "count": 1,
-            "self": 0.6125977400083684,
+            "self": 0.606251619924933,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.349335218000306,
+                    "total": 4.1704131740002595,
                     "count": 1,
-                    "self": 4.349335218000306
+                    "self": 4.1704131740002595
                 },
                 "TrainerController.advance": {
-                    "total": 497.079289960991,
+                    "total": 490.0612222990753,
                     "count": 18202,
-                    "self": 0.29963972198356714,
+                    "self": 0.27690172708707905,
                     "children": {
                         "env_step": {
-                            "total": 496.7796502390074,
+                            "total": 489.78432057198825,
                             "count": 18202,
-                            "self": 339.3249970460006,
+                            "self": 334.32922170503434,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 157.15319019402114,
+                                    "total": 155.15922617904243,
                                     "count": 18202,
-                                    "self": 1.5306453350549418,
+                                    "self": 1.5030841250522826,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 155.6225448589662,
+                                            "total": 153.65614205399015,
                                             "count": 18202,
-                                            "self": 155.6225448589662
+                                            "self": 153.65614205399015
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.3014629989856985,
+                                    "total": 0.29587268791146926,
                                     "count": 18202,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 500.67371191298525,
+                                            "total": 493.62443401508654,
                                             "count": 18202,
                                             "is_parallel": true,
-                                            "self": 247.26097797996772,
+                                            "self": 243.9692410680509,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.00699311000016678,
+                                                            "total": 0.002846171000328468,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.004740983000374399,
+                                                            "self": 0.0006944590008970408,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.002252126999792381,
+                                                                    "total": 0.002151711999431427,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.002252126999792381
+                                                                    "self": 0.002151711999431427
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04791323500012368,
+                                                            "total": 0.05210807499997827,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006505870005639736,
+                                                            "self": 0.0006189040000208479,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003086669998992875,
+                                                                    "total": 0.00042982900004062685,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003086669998992875
+                                                                    "self": 0.00042982900004062685
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.045067181999911554,
+                                                                    "total": 0.04923358699988967,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.045067181999911554
+                                                                    "self": 0.04923358699988967
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018867989997488621,
+                                                                    "total": 0.0018257550000271294,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00039101099991967203,
+                                                                    "self": 0.000371054000879667,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.00149578799982919,
+                                                                            "total": 0.0014547009991474624,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.00149578799982919
+                                                                            "self": 0.0014547009991474624
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 253.41273393301753,
+                                                    "total": 249.65519294703563,
                                                     "count": 18201,
                                                     "is_parallel": true,
-                                                    "self": 11.025201336014106,
+                                                    "self": 10.752482843070993,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.5339754340193394,
+                                                            "total": 5.48046503593423,
                                                             "count": 18201,
                                                             "is_parallel": true,
-                                                            "self": 5.5339754340193394
+                                                            "self": 5.48046503593423
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 201.8347478129822,
+                                                            "total": 198.7942765460698,
                                                             "count": 18201,
                                                             "is_parallel": true,
-                                                            "self": 201.8347478129822
+                                                            "self": 198.7942765460698
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 35.0188093500019,
+                                                            "total": 34.62796852196061,
                                                             "count": 18201,
                                                             "is_parallel": true,
-                                                            "self": 6.649840582966135,
+                                                            "self": 6.636805659996298,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 28.368968767035767,
+                                                                    "total": 27.991162861964312,
                                                                     "count": 182010,
                                                                     "is_parallel": true,
-                                                                    "self": 28.368968767035767
+                                                                    "self": 27.991162861964312
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.00011891100029970403,
+                    "total": 0.00016092999976535793,
                     "count": 1,
-                    "self": 0.00011891100029970403,
+                    "self": 0.00016092999976535793,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 492.7541749146808,
-                                    "count": 528680,
+                                    "total": 485.76029818302277,
+                                    "count": 521151,
                                     "is_parallel": true,
-                                    "self": 11.484989428783592,
+                                    "self": 11.475574856720868,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 279.0451087178967,
-                                            "count": 528680,
+                                            "total": 273.56407442129967,
+                                            "count": 521151,
                                             "is_parallel": true,
-                                            "self": 278.21819647389657,
+                                            "self": 273.0222539102997,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 0.8269122440001411,
+                                                    "total": 0.541820510999969,
                                                     "count": 4,
                                                     "is_parallel": true,
-                                                    "self": 0.8269122440001411
+                                                    "self": 0.541820510999969
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 202.2240767680005,
+                                            "total": 200.72064890500224,
                                             "count": 90,
                                             "is_parallel": true,
-                                            "self": 68.59804450401089,
+                                            "self": 68.06261840599745,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 133.6260322639896,
+                                                    "total": 132.65803049900478,
                                                     "count": 4587,
                                                     "is_parallel": true,
-                                                    "self": 133.6260322639896
+                                                    "self": 132.65803049900478
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09021638700005497,
+                    "total": 0.08592914800010476,
                     "count": 1,
-                    "self": 0.0009345339999526914,
+                    "self": 0.0009161380003206432,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08928185300010227,
+                            "total": 0.08501300999978412,
                             "count": 1,
-                            "self": 0.08928185300010227
+                            "self": 0.08501300999978412
                         }
                     }
                 }

run_logs/training_status.json

@@ -3,57 +3,57 @@
         "checkpoints": [
             {
                 "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 15.818181818181818,
-                "creation_time": 1701036585.174104,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 12.909090909090908,
+                "creation_time": 1701037996.5639346,
                 "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": 21.545454545454547,
-                "creation_time": 1701036711.5915344,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 21.09090909090909,
+                "creation_time": 1701038118.6184068,
                 "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": 25.545454545454547,
-                "creation_time": 1701036835.6909988,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 24.0,
+                "creation_time": 1701038240.1301637,
                 "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",
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
                 "reward": 26.181818181818183,
-                "creation_time": 1701036954.0669885,
+                "creation_time": 1701038359.5553951,
                 "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": 26.181818181818183,
-                "creation_time": 1701036954.1824985,
+                "steps": 200200,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200200.onnx",
+                "reward": 25.272727272727273,
+                "creation_time": 1701038359.68996,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-200200.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 26.181818181818183,
-            "creation_time": 1701036954.1824985,
+            "steps": 200200,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 25.272727272727273,
+            "creation_time": 1701038359.68996,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-200200.pt"
             ]
         }
     },