First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd5f361d5bbd37bb099f7e614e9a7ec70d7dc920e61dfb63c32f2543d1f4925
+oid sha256:05bf3762986b1e9858edbc935f0d852f205a293a047075e6199b64618edeeae3
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e28fc1f98db763a4169910290fe65c39939b07c8d7f783ff354fff3a5a856f8
+oid sha256:42f35d7a0a0261150b54a9838de3a8e9303ec7e8a8cce3ee1e0ef95375b41ca3
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48fb54bbbb5f58e62bba2e55380f0b42a0ecc61a7fb89a10c10c708d6187b1b8
+oid sha256:15c12e32b1f1e7134360397317e33779321e52fb35464d655fd0ebdf8587e671
 size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd5f361d5bbd37bb099f7e614e9a7ec70d7dc920e61dfb63c32f2543d1f4925
+oid sha256:05bf3762986b1e9858edbc935f0d852f205a293a047075e6199b64618edeeae3
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:505bbb16883c38686abdb550bb1970c1137f29fda0e5294ce371935e2fa19ae8
+oid sha256:421521131e42928c145d7c47c7eb8f1322d2f44eea24be3d3bf43b2cb495b11d
 size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd5f361d5bbd37bb099f7e614e9a7ec70d7dc920e61dfb63c32f2543d1f4925
+oid sha256:05bf3762986b1e9858edbc935f0d852f205a293a047075e6199b64618edeeae3
 size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:505d87c20f83cfc922fd602557ecc26ad4a65f138a79098521fc6fcbfaf107e1
+oid sha256:4ee86b1ac05ba5fd790eab0aaba3b733fe4cd892506610f118c8677105cc8b05
 size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d113fc89637c89df6d80f8e14ad7eea8b215f3cf40be4edf28a44fd872adda
+oid sha256:3c3652bbe11604b46af0ee95123c85e68c98825b227fe3d12bf3c93998452780
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fd4391fba82796d9af54a2e88c661dfc0329eccbbb44e15bba28fca88e8c380
+oid sha256:15a3a7419d8fcfb64fc0bd2f64223b029ee80f2011cbdaac45bd63fad6cf91b8
 size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a26a753cc06199e20c14ddda7d04d2ea238e5d413f9dccc310fa34b0b23b829
+oid sha256:11e2e9092f44bedc0741d3239d84ac5a5336d825755efc003055c49dbbdcbd3c
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8144536eb72accee8fba92cae26ec2fb5be002dd100ab070f45d64d5adeb42c
+oid sha256:67179bb7838aacc11447c25b446344f2f6633a3b41e6dd9b8d45fec60f78be84
 size 3850000

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c727b59a97ca2379f809d12fb5a1d2906789d8dceb211cd981f844883cc8855
+oid sha256:da99862bc584774070785c0b4bb11861b7c1853e21112a9f84777d42d777c0ec
 size 3849250

SnowballTarget/events.out.tfevents.1711814671.9606770bb8c5.10039.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b3bc492a0d7cd5ce9717814f3910fcf7d096f66e4b376afedd37026e337ac1
+size 23588

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": "SnowballTarget_1", "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": 4, "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": "SnowballTarget_2", "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

@@ -9,7 +9,7 @@ behaviors:
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
-      num_epoch: 3
+      num_epoch: 4
       shared_critic: false
       learning_rate_schedule: linear
       beta_schedule: linear
@@ -66,7 +66,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget_1
+  run_id: SnowballTarget_2
   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  0.088 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)
@@ -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: 0.667501 ms
+UnloadTime: 0.741512 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.
@@ -169,7 +166,7 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 38
+  Peak main deferred allocation count 41
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
@@ -178,13 +175,13 @@ Memory Statistics:
       Peak usage frame count: [4.0 MB-8.0 MB]: 5460 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]: 5460 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.4 MB
+      Peak Allocated memory 17.8 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -213,10 +210,10 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4742 frames, [64.0 KB-128.0 KB]: 718 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4797 frames, [64.0 KB-128.0 KB]: 663 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.4 KB
+      Peak Allocated memory 66.8 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
       Peak usage frame count: [32.0 KB-64.0 KB]: 5460 frames

run_logs/timers.json

@@ -2,15 +2,15 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.9567068219184875,
-            "min": 0.9567068219184875,
-            "max": 2.852590322494507,
+            "value": 0.7965793013572693,
+            "min": 0.7965793013572693,
+            "max": 2.861267328262329,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 9134.63671875,
-            "min": 9134.63671875,
-            "max": 29213.376953125,
+            "value": 7605.7392578125,
+            "min": 7605.7392578125,
+            "max": 29333.712890625,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.80202865600586,
-            "min": 0.3374572694301605,
-            "max": 12.80202865600586,
+            "value": 13.157942771911621,
+            "min": 0.4909791052341461,
+            "max": 13.157942771911621,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2496.3955078125,
-            "min": 65.46671295166016,
-            "max": 2594.75927734375,
+            "value": 2565.798828125,
+            "min": 95.24994659423828,
+            "max": 2652.36474609375,
             "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,87 +50,87 @@
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07643159101551682,
-            "min": 0.06420564808050747,
-            "max": 0.07643159101551682,
+            "value": 0.07365348233254147,
+            "min": 0.062463727970252333,
+            "max": 0.07365348233254147,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.30572636406206727,
-            "min": 0.26307252615016274,
-            "max": 0.369977058580273,
+            "value": 0.2946139293301659,
+            "min": 0.24985491188100933,
+            "max": 0.35580952290740026,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.19654907717132103,
-            "min": 0.12440401481866252,
-            "max": 0.30611378410283263,
+            "value": 0.18339906156282212,
+            "min": 0.11749263923967887,
+            "max": 0.2594315111637115,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7861963086852841,
-            "min": 0.4976160592746501,
-            "max": 1.530568920514163,
+            "value": 0.7335962462512885,
+            "min": 0.4699705569587155,
+            "max": 1.2971575558185575,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
+            "value": 8.082097306000007e-06,
+            "min": 8.082097306000007e-06,
             "max": 0.000291882002706,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
+            "value": 3.232838922400003e-05,
+            "min": 3.232838922400003e-05,
+            "max": 0.0013851600382800001,
             "count": 20
         },
         "SnowballTarget.Policy.Epsilon.mean": {
             "value": 0.10269400000000001,
             "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
+            "max": 0.197294,
             "count": 20
         },
         "SnowballTarget.Policy.Epsilon.sum": {
             "value": 0.41077600000000003,
             "min": 0.41077600000000003,
-            "max": 0.96172,
+            "max": 0.9617200000000001,
             "count": 20
         },
         "SnowballTarget.Policy.Beta.mean": {
             "value": 0.0001444306000000001,
             "min": 0.0001444306000000001,
-            "max": 0.0048649706,
+            "max": 0.004864970599999999,
             "count": 20
         },
         "SnowballTarget.Policy.Beta.sum": {
             "value": 0.0005777224000000004,
             "min": 0.0005777224000000004,
-            "max": 0.023089828,
+            "max": 0.023089828000000003,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 25.204545454545453,
-            "min": 3.5681818181818183,
-            "max": 25.363636363636363,
+            "value": 25.863636363636363,
+            "min": 3.4318181818181817,
+            "max": 26.09090909090909,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1109.0,
-            "min": 157.0,
-            "max": 1395.0,
+            "value": 1138.0,
+            "min": 151.0,
+            "max": 1435.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 25.204545454545453,
-            "min": 3.5681818181818183,
-            "max": 25.363636363636363,
+            "value": 25.863636363636363,
+            "min": 3.4318181818181817,
+            "max": 26.09090909090909,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1109.0,
-            "min": 157.0,
-            "max": 1395.0,
+            "value": 1138.0,
+            "min": 151.0,
+            "max": 1435.0,
             "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1711813491",
+        "start_time_seconds": "1711814671",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTarget_1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget_2 --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.2.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1711813978"
+        "end_time_seconds": "1711815177"
     },
-    "total": 486.79996269599997,
+    "total": 505.92118633599966,
     "count": 1,
-    "self": 0.432276629999933,
+    "self": 0.478293470999688,
     "children": {
         "run_training.setup": {
-            "total": 0.05428952600004777,
+            "total": 0.0508603180001046,
             "count": 1,
-            "self": 0.05428952600004777
+            "self": 0.0508603180001046
         },
         "TrainerController.start_learning": {
-            "total": 486.31339654,
+            "total": 505.39203254699987,
             "count": 1,
-            "self": 0.6012987409635571,
+            "self": 0.5827457259888433,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.8597135789998447,
+                    "total": 1.9353972330000033,
                     "count": 1,
-                    "self": 2.8597135789998447
+                    "self": 1.9353972330000033
                 },
                 "TrainerController.advance": {
-                    "total": 482.7554564390366,
+                    "total": 502.7830070160112,
                     "count": 18199,
-                    "self": 0.3110593270403115,
+                    "self": 0.289797671955057,
                     "children": {
                         "env_step": {
-                            "total": 482.4443971119963,
+                            "total": 502.49320934405614,
                             "count": 18199,
-                            "self": 312.52565975996913,
+                            "self": 334.5084811870879,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 169.60887636002326,
+                                    "total": 167.68619183196734,
                                     "count": 18199,
-                                    "self": 1.6190398749981796,
+                                    "self": 1.5793524900013836,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 167.98983648502508,
+                                            "total": 166.10683934196595,
                                             "count": 18199,
-                                            "self": 167.98983648502508
+                                            "self": 166.10683934196595
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.30986099200390527,
+                                    "total": 0.2985363250008959,
                                     "count": 18199,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 484.9942482109825,
+                                            "total": 504.14980582205226,
                                             "count": 18199,
                                             "is_parallel": true,
-                                            "self": 241.87021718698747,
+                                            "self": 269.17307836503824,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.00596287400003348,
+                                                            "total": 0.0023864780000621977,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0041948640000555315,
+                                                            "self": 0.0007074210011523974,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0017680099999779486,
+                                                                    "total": 0.0016790569989098003,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0017680099999779486
+                                                                    "self": 0.0016790569989098003
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04504425499999343,
+                                                            "total": 0.039732972999900085,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007148140002755099,
+                                                            "self": 0.0007441459997608035,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00044029199989381596,
+                                                                    "total": 0.00040609600000607315,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00044029199989381596
+                                                                    "self": 0.00040609600000607315
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04167633499992007,
+                                                                    "total": 0.03622750400018049,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04167633499992007
+                                                                    "self": 0.03622750400018049
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0022128139999040286,
+                                                                    "total": 0.0023552269999527198,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00044376799996825866,
+                                                                    "self": 0.0004313509998610243,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.00176904599993577,
+                                                                            "total": 0.0019238760000916955,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.00176904599993577
+                                                                            "self": 0.0019238760000916955
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 243.12403102399503,
+                                                    "total": 234.97672745701402,
                                                     "count": 18198,
                                                     "is_parallel": true,
-                                                    "self": 10.93895692802812,
+                                                    "self": 10.844048338034554,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.978166876970818,
+                                                            "total": 5.8218318570225165,
                                                             "count": 18198,
                                                             "is_parallel": true,
-                                                            "self": 5.978166876970818
+                                                            "self": 5.8218318570225165
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 188.79059470600055,
+                                                            "total": 181.59153125093917,
                                                             "count": 18198,
                                                             "is_parallel": true,
-                                                            "self": 188.79059470600055
+                                                            "self": 181.59153125093917
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 37.416312512995546,
+                                                            "total": 36.71931601101778,
                                                             "count": 18198,
                                                             "is_parallel": true,
-                                                            "self": 7.034112623965939,
+                                                            "self": 6.885056439073196,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 30.382199889029607,
+                                                                    "total": 29.834259571944585,
                                                                     "count": 181980,
                                                                     "is_parallel": true,
-                                                                    "self": 30.382199889029607
+                                                                    "self": 29.834259571944585
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.00013931200010119937,
+                    "total": 0.00014016399973115767,
                     "count": 1,
-                    "self": 0.00013931200010119937,
+                    "self": 0.00014016399973115767,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 476.51047671214747,
-                                    "count": 716808,
+                                    "total": 496.4783875168664,
+                                    "count": 700008,
                                     "is_parallel": true,
-                                    "self": 15.676240153193248,
+                                    "self": 16.220282634042178,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 263.2987403209552,
-                                            "count": 716808,
+                                            "total": 257.3785882338234,
+                                            "count": 700008,
                                             "is_parallel": true,
-                                            "self": 262.5565500639548,
+                                            "self": 256.83755923482295,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 0.7421902570004022,
+                                                    "total": 0.5410289990004458,
                                                     "count": 4,
                                                     "is_parallel": true,
-                                                    "self": 0.7421902570004022
+                                                    "self": 0.5410289990004458
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 197.53549623799904,
+                                            "total": 222.87951664900083,
                                             "count": 90,
                                             "is_parallel": true,
-                                            "self": 56.79567180400795,
+                                            "self": 68.06298923500799,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 140.7398244339911,
-                                                    "count": 4584,
+                                                    "total": 154.81652741399284,
+                                                    "count": 6116,
                                                     "is_parallel": true,
-                                                    "self": 140.7398244339911
+                                                    "self": 154.81652741399284
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09678846899987548,
+                    "total": 0.09074240800009648,
                     "count": 1,
-                    "self": 0.0009136709998074366,
+                    "self": 0.001034858000366512,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09587479800006804,
+                            "total": 0.08970754999972996,
                             "count": 1,
-                            "self": 0.09587479800006804
+                            "self": 0.08970754999972996
                         }
                     }
                 }

run_logs/training_status.json

@@ -3,57 +3,57 @@
         "checkpoints": [
             {
                 "steps": 49936,
-                "file_path": "results/SnowballTarget_1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 13.909090909090908,
-                "creation_time": 1711813617.8049924,
+                "file_path": "results/SnowballTarget_2/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 14.0,
+                "creation_time": 1711814801.783286,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget_1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget_2/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             },
             {
                 "steps": 99960,
-                "file_path": "results/SnowballTarget_1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 19.818181818181817,
-                "creation_time": 1711813738.540396,
+                "file_path": "results/SnowballTarget_2/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 22.181818181818183,
+                "creation_time": 1711814926.479054,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget_1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget_2/SnowballTarget/SnowballTarget-99960.pt"
                 ]
             },
             {
                 "steps": 149984,
-                "file_path": "results/SnowballTarget_1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 24.818181818181817,
-                "creation_time": 1711813860.3873217,
+                "file_path": "results/SnowballTarget_2/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 25.181818181818183,
+                "creation_time": 1711815051.1420293,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget_1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget_2/SnowballTarget/SnowballTarget-149984.pt"
                 ]
             },
             {
                 "steps": 199984,
-                "file_path": "results/SnowballTarget_1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.636363636363637,
-                "creation_time": 1711813977.9986396,
+                "file_path": "results/SnowballTarget_2/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.181818181818183,
+                "creation_time": 1711815176.589841,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget_1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget_2/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
                 "steps": 200112,
-                "file_path": "results/SnowballTarget_1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.636363636363637,
-                "creation_time": 1711813978.123454,
+                "file_path": "results/SnowballTarget_2/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 25.181818181818183,
+                "creation_time": 1711815176.709165,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget_1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget_2/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
             "steps": 200112,
-            "file_path": "results/SnowballTarget_1/SnowballTarget.onnx",
-            "reward": 25.636363636363637,
-            "creation_time": 1711813978.123454,
+            "file_path": "results/SnowballTarget_2/SnowballTarget.onnx",
+            "reward": 25.181818181818183,
+            "creation_time": 1711815176.709165,
             "auxillary_file_paths": [
-                "results/SnowballTarget_1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget_2/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },