First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b4e2804620dc7dc0aaff872c0c863f2c816a0d77f727b85df8a8d2971b2f0d8
+oid sha256:9eef91f46a7e79a4fa0666cece9e2543c0b56b6599d414923dfe1716b71488d0
 size 646532

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbe2c6669920bbe2a3a92cee23581fa6cd9acc3d2ca2e091eff5867f476c8117
+oid sha256:3c0580a7272823af440943630899eea4458cdbbbff5bb87386a8b3cfd33802e5
 size 646532

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e86a0ef1c7499f5423c1bd016f062e8d51f496df2815a77666b06be742c060d
+oid sha256:a7ce99fe62360d82188acea16facc4c9cdaae04257d1184bb9ed1f8e3537c4e0
 size 3843968

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b4e2804620dc7dc0aaff872c0c863f2c816a0d77f727b85df8a8d2971b2f0d8
+oid sha256:9eef91f46a7e79a4fa0666cece9e2543c0b56b6599d414923dfe1716b71488d0
 size 646532

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d042ab14a3f48912575d87c382323c740af2d38eae8fcd428aa5e64d65c111a
+oid sha256:801e971b10a9a9209d1c352377dd40566814d2903a15fd426f0de99fb15e663c
 size 3843968

SnowballTarget/SnowballTarget-200200.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eef91f46a7e79a4fa0666cece9e2543c0b56b6599d414923dfe1716b71488d0
+size 646532

SnowballTarget/SnowballTarget-200200.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b9ea83c43095f1976ead6edbf2ce43bf098881119d70e3722a9c5a2138dc35
+size 3843968

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4b135e3943b89a62fc82f43815af8937bea1810b79336c10bc7327d782d96f
+oid sha256:fb5b5db4505b70a887a999285e1e931f7d88d0b94fa637fe3b3fdede2adccbf0
 size 646532

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ac07b24f9d64703d9792350f35946d1db0eccdd54716d2ca8aa8654e7cf8cc1
+oid sha256:e99d7e53948dfc0aa770a385b7ccd2175fbcac03072a00270928f72f9b18536e
 size 3843968

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45b7ee6e5366751990ec9d77e76f9148c1235c6e7d76d4adc0b8e07b9590818a
+oid sha256:bc6d448922bd0f1235d0f3327e98ae3bb8462ddfc66baeb6546b40e494dc4e48
 size 646532

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae032fd1dfbd74228dc2fc4edc6b3c8d733a97ca3f7a6035584880256efd65c
+oid sha256:26ebe5a2ad5d97867ad72b7f6471f89710c6280ae612e936ab92f97ec57e7666
 size 3843968

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32764a038f01af5a449e7d1e567f3e47bec1c66e3301dac54825455bb45ffae4
+oid sha256:c7b9ea83c43095f1976ead6edbf2ce43bf098881119d70e3722a9c5a2138dc35
 size 3843968

SnowballTarget/events.out.tfevents.1686387465.f9711cf69cef.1105.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe3ba0bcdb992e36965d0263ccac0c74b594b19d588bee615902b9eb6e8fe03
+size 28813

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, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget11", "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, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget", "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

@@ -64,7 +64,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget11
+  run_id: SnowballTarget
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -2,6 +2,9 @@ Mono path[0] = '/content/ml-agents-patch/training-envs-executables/linux/Snowbal
 Mono config path = '/content/ml-agents-patch/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-patch/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -31,7 +34,7 @@ ALSA lib pcm.c:2642:(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  0.090 seconds
+- Completed reload, in  0.084 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -42,7 +45,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.664345 ms
+UnloadTime: 0.668085 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -166,7 +169,7 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 47
+  Peak main deferred allocation count 41
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
@@ -175,7 +178,7 @@ Memory Statistics:
       Peak usage frame count: [4.0 MB-8.0 MB]: 5462 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 6.7 MB
+      Peak Allocated memory 6.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
       Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
@@ -210,10 +213,10 @@ 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]: 4647 frames, [64.0 KB-128.0 KB]: 815 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4445 frames, [64.0 KB-128.0 KB]: 1017 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.8 KB
+      Peak Allocated memory 67.3 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
       Peak usage frame count: [32.0 KB-64.0 KB]: 5462 frames

run_logs/timers.json

@@ -2,15 +2,15 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.9829342365264893,
-            "min": 0.9829342365264893,
-            "max": 2.865917205810547,
+            "value": 1.0653297901153564,
+            "min": 1.0653297901153564,
+            "max": 2.858488082885742,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 9395.8681640625,
-            "min": 9395.8681640625,
-            "max": 29381.3828125,
+            "value": 10183.4873046875,
+            "min": 10183.4873046875,
+            "max": 29273.77734375,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.623763084411621,
-            "min": 0.36927610635757446,
-            "max": 12.623763084411621,
+            "value": 12.638876914978027,
+            "min": 0.36404725909233093,
+            "max": 12.638876914978027,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2461.6337890625,
-            "min": 71.63956451416016,
-            "max": 2525.593017578125,
+            "value": 2464.5810546875,
+            "min": 70.62516784667969,
+            "max": 2563.384765625,
             "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07280002598246724,
-            "min": 0.06108100912971685,
-            "max": 0.07529431707956188,
+            "value": 0.06756832470066501,
+            "min": 0.06126134650320654,
+            "max": 0.07445792262716328,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.29120010392986895,
-            "min": 0.25601398065405456,
-            "max": 0.36138179990880687,
+            "value": 0.27027329880266004,
+            "min": 0.24504538601282616,
+            "max": 0.3722896131358164,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.21106607992859447,
-            "min": 0.12309441370569973,
-            "max": 0.2818194264874738,
+            "value": 0.2581539674132478,
+            "min": 0.15281490772259515,
+            "max": 0.2732131793072411,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.8442643197143779,
-            "min": 0.49237765482279894,
-            "max": 1.4090971324373691,
+            "value": 1.0326158696529912,
+            "min": 0.6112596308903806,
+            "max": 1.3492888837468389,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 25.113636363636363,
-            "min": 3.25,
-            "max": 25.29090909090909,
+            "value": 24.886363636363637,
+            "min": 3.772727272727273,
+            "max": 24.90909090909091,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1105.0,
-            "min": 143.0,
-            "max": 1391.0,
+            "value": 1095.0,
+            "min": 166.0,
+            "max": 1370.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 25.113636363636363,
-            "min": 3.25,
-            "max": 25.29090909090909,
+            "value": 24.886363636363637,
+            "min": 3.772727272727273,
+            "max": 24.90909090909091,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1105.0,
-            "min": 143.0,
-            "max": 1391.0,
+            "value": 1095.0,
+            "min": 166.0,
+            "max": 1370.0,
             "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1686342282",
+        "start_time_seconds": "1686387464",
         "python_version": "3.10.12 (main, Jun  7 2023, 12:45:35) [GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget11 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget --no-graphics",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1686342783"
+        "end_time_seconds": "1686387940"
     },
-    "total": 500.689434057,
+    "total": 476.149789041,
     "count": 1,
-    "self": 0.42702736600000435,
+    "self": 0.4313932070000419,
     "children": {
         "run_training.setup": {
-            "total": 0.04125100900000689,
+            "total": 0.043099917999995796,
             "count": 1,
-            "self": 0.04125100900000689
+            "self": 0.043099917999995796
         },
         "TrainerController.start_learning": {
-            "total": 500.221155682,
+            "total": 475.675295916,
             "count": 1,
-            "self": 0.5725422419995994,
+            "self": 0.6231617049925262,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.908960798999999,
+                    "total": 4.137711034999995,
                     "count": 1,
-                    "self": 3.908960798999999
+                    "self": 4.137711034999995
                 },
                 "TrainerController.advance": {
-                    "total": 495.5872944550004,
+                    "total": 470.78015949700756,
                     "count": 18204,
-                    "self": 0.28807763799363784,
+                    "self": 0.2754055160073108,
                     "children": {
                         "env_step": {
-                            "total": 495.29921681700677,
+                            "total": 470.50475398100025,
                             "count": 18204,
-                            "self": 360.16837258400165,
+                            "self": 345.81845625501,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 134.84929339200482,
+                                    "total": 124.40468182899639,
                                     "count": 18204,
-                                    "self": 1.8046705460168369,
+                                    "self": 1.8459019109993164,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 133.044622845988,
+                                            "total": 122.55877991799707,
                                             "count": 18204,
-                                            "self": 133.044622845988
+                                            "self": 122.55877991799707
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.28155084100029626,
+                                    "total": 0.28161589699382716,
                                     "count": 18204,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 498.527873404001,
+                                            "total": 474.10254149799437,
                                             "count": 18204,
                                             "is_parallel": true,
-                                            "self": 236.90754103900332,
+                                            "self": 220.06562533399813,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0027379279999877326,
+                                                            "total": 0.005703778999986753,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007037219999688205,
+                                                            "self": 0.004112338999959775,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.002034206000018912,
+                                                                    "total": 0.001591440000026978,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.002034206000018912
+                                                                    "self": 0.001591440000026978
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.049086267000006956,
+                                                            "total": 0.052595511999982136,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000500081999973645,
+                                                            "self": 0.0006636710000123003,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003881110000065746,
+                                                                    "total": 0.0003221030000020164,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003881110000065746
+                                                                    "self": 0.0003221030000020164
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0459134449999965,
+                                                                    "total": 0.04946189399998957,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0459134449999965
+                                                                    "self": 0.04946189399998957
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002284629000030236,
+                                                                    "total": 0.0021478439999782495,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005715790001090681,
+                                                                    "self": 0.0003648979999297808,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001713049999921168,
+                                                                            "total": 0.0017829460000484687,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001713049999921168
+                                                                            "self": 0.0017829460000484687
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 261.6203323649977,
+                                                    "total": 254.03691616399624,
                                                     "count": 18203,
                                                     "is_parallel": true,
-                                                    "self": 10.724119716005873,
+                                                    "self": 10.576325412007378,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.7101396779913784,
+                                                            "total": 5.3421877689913515,
                                                             "count": 18203,
                                                             "is_parallel": true,
-                                                            "self": 5.7101396779913784
+                                                            "self": 5.3421877689913515
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 206.99653442599777,
+                                                            "total": 203.22721400599457,
                                                             "count": 18203,
                                                             "is_parallel": true,
-                                                            "self": 206.99653442599777
+                                                            "self": 203.22721400599457
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 38.18953854500268,
+                                                            "total": 34.89118897700294,
                                                             "count": 18203,
                                                             "is_parallel": true,
-                                                            "self": 7.022838214011188,
+                                                            "self": 6.285768090999568,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 31.16670033099149,
+                                                                    "total": 28.605420886003373,
                                                                     "count": 182030,
                                                                     "is_parallel": true,
-                                                                    "self": 31.16670033099149
+                                                                    "self": 28.605420886003373
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.224300004007091e-05,
+                    "total": 0.0001696159999937663,
                     "count": 1,
-                    "self": 9.224300004007091e-05,
+                    "self": 0.0001696159999937663,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 491.62902670200634,
-                                    "count": 466500,
+                                    "total": 467.0786967380349,
+                                    "count": 462394,
                                     "is_parallel": true,
-                                    "self": 10.759211416984726,
+                                    "self": 9.9716951830531,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 268.79954234602116,
-                                            "count": 466500,
+                                            "total": 255.84439582698175,
+                                            "count": 462394,
                                             "is_parallel": true,
-                                            "self": 267.48715303802123,
+                                            "self": 254.98892250198176,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 1.312389307999922,
+                                                    "total": 0.8554733249999913,
                                                     "count": 4,
                                                     "is_parallel": true,
-                                                    "self": 1.312389307999922
+                                                    "self": 0.8554733249999913
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 212.07027293900046,
+                                            "total": 201.26260572800004,
                                             "count": 90,
                                             "is_parallel": true,
-                                            "self": 85.47357697099812,
+                                            "self": 78.3491579639983,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 126.59669596800234,
+                                                    "total": 122.91344776400175,
                                                     "count": 4587,
                                                     "is_parallel": true,
-                                                    "self": 126.59669596800234
+                                                    "self": 122.91344776400175
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.15226594299997487,
+                    "total": 0.13409406299990678,
                     "count": 1,
-                    "self": 0.0009300809999785997,
+                    "self": 0.0009151099999371581,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.15133586199999627,
+                            "total": 0.13317895299996962,
                             "count": 1,
-                            "self": 0.15133586199999627
+                            "self": 0.13317895299996962
                         }
                     }
                 }

run_logs/training_status.json

@@ -3,57 +3,57 @@
         "checkpoints": [
             {
                 "steps": 49936,
-                "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 12.363636363636363,
-                "creation_time": 1686342413.370025,
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 12.818181818181818,
+                "creation_time": 1686387589.7630868,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget11/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             },
             {
                 "steps": 99960,
-                "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-99960.onnx",
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-99960.onnx",
                 "reward": 19.636363636363637,
-                "creation_time": 1686342538.611239,
+                "creation_time": 1686387708.8694067,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget11/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-99960.pt"
                 ]
             },
             {
                 "steps": 149984,
-                "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 24.09090909090909,
-                "creation_time": 1686342660.3551714,
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 23.181818181818183,
+                "creation_time": 1686387825.2703478,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget11/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-149984.pt"
                 ]
             },
             {
                 "steps": 199984,
-                "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.363636363636363,
-                "creation_time": 1686342782.9023669,
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 24.272727272727273,
+                "creation_time": 1686387940.3579473,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget11/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.363636363636363,
-                "creation_time": 1686342783.0883267,
+                "steps": 200200,
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-200200.onnx",
+                "reward": 24.90909090909091,
+                "creation_time": 1686387940.5462108,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget11/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-200200.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget11/SnowballTarget.onnx",
-            "reward": 25.363636363636363,
-            "creation_time": 1686342783.0883267,
+            "steps": 200200,
+            "file_path": "results/SnowballTarget/SnowballTarget.onnx",
+            "reward": 24.90909090909091,
+            "creation_time": 1686387940.5462108,
             "auxillary_file_paths": [
-                "results/SnowballTarget11/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget/SnowballTarget/SnowballTarget-200200.pt"
             ]
         }
     },