First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83e90e874b1e8bf976d161ee08b55fed36393d8f88bc1d7a65eb87774ae33fe3
+oid sha256:3ff58e567f26b0ff8304c3908047d11baea26d70e758e1fb01f691a175afc3d0
 size 646532

SnowballTarget/SnowballTarget-249984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4762accd0802ded289bf8e5a80a8af14b81fe389d792ca37a2728282bf7f6039
+size 646532

SnowballTarget/SnowballTarget-249984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:111de03a05f8e3d1b0262a1f8ff27b83b9ace9d19f00d2d505b40c5f74ea6833
+size 3843968

SnowballTarget/SnowballTarget-279224.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ff58e567f26b0ff8304c3908047d11baea26d70e758e1fb01f691a175afc3d0
+size 646532

SnowballTarget/SnowballTarget-279224.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7479627a0eaf3b6c745b518b94b4c89069577ec273705801364499ea9113805e
+size 3843968

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a73343a095ed2eeb02eeab9da9b29e1312ee44436c94ebb99f0a8a5a76fb81c
+oid sha256:7479627a0eaf3b6c745b518b94b4c89069577ec273705801364499ea9113805e
 size 3843968

SnowballTarget/events.out.tfevents.1696418835.c21b34188a69.10739.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a493905dba7e4eaa56b6f2ccc0427e8f857d10dec5b30800e68d69d1799019d
+size 6868

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": "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": 500000, "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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 200000
+    max_steps: 500000
     time_horizon: 64
     summary_freq: 10000
     threaded: true
@@ -67,7 +67,7 @@ checkpoint_settings:
   run_id: SnowballTarget1
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: 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  0.081 seconds
+- Completed reload, in  0.085 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)
@@ -45,15 +42,17 @@ 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: 0.730506 ms
+UnloadTime: 0.660902 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.
+abort_threads: Failed aborting id: 0x7a64190ba640, mono_thread_manage will ignore it
+
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5374 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 2143 frames, [16.0 KB-32.0 KB]: 36 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -169,22 +168,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 45
+  Peak main deferred allocation count 41
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 5466 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 2180 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 6.9 MB
+      Peak Allocated memory 6.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5466 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 2180 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.6 MB
+      Peak Allocated memory 17.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -213,13 +212,13 @@ 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]: 3836 frames, [64.0 KB-128.0 KB]: 1630 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 2050 frames, [64.0 KB-128.0 KB]: 130 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 67.3 KB
+      Peak Allocated memory 67.2 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5466 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 2180 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +230,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5466 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 2180 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5465 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 2179 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -249,13 +248,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5466 frames
+      Peak usage frame count: [0-1.0 KB]: 2180 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 5466 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 2180 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,213 +2,213 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 1.053622841835022,
-            "min": 1.048506259918213,
-            "max": 2.849545478820801,
-            "count": 20
+            "value": 0.9509430527687073,
+            "min": 0.9332674741744995,
+            "max": 1.0425547361373901,
+            "count": 7
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 10071.5810546875,
-            "min": 9965.0029296875,
-            "max": 29213.541015625,
-            "count": 20
+            "value": 9675.845703125,
+            "min": 8900.787109375,
+            "max": 10665.3349609375,
+            "count": 7
         },
         "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "value": 269976.0,
+            "min": 209936.0,
+            "max": 269976.0,
+            "count": 7
         },
         "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "value": 269976.0,
+            "min": 209936.0,
+            "max": 269976.0,
+            "count": 7
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.18110179901123,
-            "min": 0.561591386795044,
-            "max": 12.18110179901123,
-            "count": 20
+            "value": 13.233717918395996,
+            "min": 12.270806312561035,
+            "max": 13.233717918395996,
+            "count": 7
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2375.31494140625,
-            "min": 108.94873046875,
-            "max": 2465.064453125,
-            "count": 20
+            "value": 2580.574951171875,
+            "min": 2355.994873046875,
+            "max": 2664.337890625,
+            "count": 7
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 20
+            "count": 7
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
             "value": 8756.0,
             "min": 8756.0,
             "max": 10945.0,
-            "count": 20
+            "count": 7
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07262397972169543,
-            "min": 0.058846979212081776,
-            "max": 0.07639560557801423,
-            "count": 20
+            "value": 0.06434979716241108,
+            "min": 0.06434979716241108,
+            "max": 0.07744694704314872,
+            "count": 7
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2904959188867817,
-            "min": 0.2353879168483271,
-            "max": 0.3819780278900711,
-            "count": 20
+            "value": 0.25739918864964434,
+            "min": 0.25739918864964434,
+            "max": 0.3872347352157436,
+            "count": 7
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.1541597118199456,
-            "min": 0.12193502654326058,
-            "max": 0.2728895098555322,
-            "count": 20
+            "value": 0.17866915223353047,
+            "min": 0.17456258690970783,
+            "max": 0.19856594356836058,
+            "count": 7
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.6166388472797824,
-            "min": 0.4877401061730423,
-            "max": 1.3644475492776609,
-            "count": 20
+            "value": 0.7146766089341219,
+            "min": 0.6982503476388313,
+            "max": 0.9928297178418029,
+            "count": 7
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
+            "value": 0.00014104565298479998,
+            "min": 0.00014104565298479998,
+            "max": 0.00017668564110480002,
+            "count": 7
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
-            "count": 20
+            "value": 0.0005641826119391999,
+            "min": 0.0005641826119391999,
+            "max": 0.000853728215424,
+            "count": 7
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
+            "value": 0.1470152,
+            "min": 0.1470152,
+            "max": 0.15889520000000001,
+            "count": 7
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
-            "count": 20
+            "value": 0.5880608,
+            "min": 0.5880608,
+            "max": 0.7845760000000002,
+            "count": 7
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
+            "value": 0.00235605848,
+            "min": 0.00235605848,
+            "max": 0.002948870480000001,
+            "count": 7
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828,
-            "count": 20
+            "value": 0.00942423392,
+            "min": 0.00942423392,
+            "max": 0.0142503424,
+            "count": 7
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 24.045454545454547,
-            "min": 3.590909090909091,
-            "max": 24.363636363636363,
-            "count": 20
+            "value": 25.954545454545453,
+            "min": 23.818181818181817,
+            "max": 25.954545454545453,
+            "count": 7
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1058.0,
-            "min": 158.0,
-            "max": 1294.0,
-            "count": 20
+            "value": 1142.0,
+            "min": 1048.0,
+            "max": 1411.0,
+            "count": 7
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 24.045454545454547,
-            "min": 3.590909090909091,
-            "max": 24.363636363636363,
-            "count": 20
+            "value": 25.954545454545453,
+            "min": 23.818181818181817,
+            "max": 25.954545454545453,
+            "count": 7
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1058.0,
-            "min": 158.0,
-            "max": 1294.0,
-            "count": 20
+            "value": 1142.0,
+            "min": 1048.0,
+            "max": 1411.0,
+            "count": 7
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 7
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 7
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1696417247",
+        "start_time_seconds": "1696418834",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ppo.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ppo.yaml --resume --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1696417770"
+        "end_time_seconds": "1696419045"
     },
-    "total": 522.557199196,
+    "total": 211.43181110000023,
     "count": 1,
-    "self": 0.8382067149999557,
+    "self": 0.008607448000020668,
     "children": {
         "run_training.setup": {
-            "total": 0.04451184300000932,
+            "total": 0.04204078000020672,
             "count": 1,
-            "self": 0.04451184300000932
+            "self": 0.04204078000020672
         },
         "TrainerController.start_learning": {
-            "total": 521.6744806380001,
+            "total": 211.381162872,
             "count": 1,
-            "self": 0.6700808120075408,
+            "self": 0.8524889690129385,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.432653024000047,
+                    "total": 4.148062613000093,
                     "count": 1,
-                    "self": 5.432653024000047
+                    "self": 4.148062613000093
                 },
                 "TrainerController.advance": {
-                    "total": 515.3198458849924,
-                    "count": 18217,
-                    "self": 0.31556762899072055,
+                    "total": 206.06741542598684,
+                    "count": 7264,
+                    "self": 0.12974490201804656,
                     "children": {
                         "env_step": {
-                            "total": 515.0042782560017,
-                            "count": 18217,
-                            "self": 376.14435332499056,
+                            "total": 205.9376705239688,
+                            "count": 7264,
+                            "self": 150.14040884797123,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 138.4456036400095,
-                                    "count": 18217,
-                                    "self": 1.9172772690005786,
+                                    "total": 55.66749211900424,
+                                    "count": 7264,
+                                    "self": 0.7677587529815355,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 136.52832637100892,
-                                            "count": 18217,
-                                            "self": 136.52832637100892
+                                            "total": 54.8997333660227,
+                                            "count": 7264,
+                                            "self": 54.8997333660227
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.41432129100167003,
-                                    "count": 18217,
+                                    "total": 0.12976955699332393,
+                                    "count": 7264,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 519.8660511109985,
-                                            "count": 18217,
+                                            "total": 209.2923571470028,
+                                            "count": 7264,
                                             "is_parallel": true,
-                                            "self": 243.98104286701096,
+                                            "self": 99.49096950098556,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.006872843999985889,
+                                                            "total": 0.002168768000046839,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.005064880999839261,
+                                                            "self": 0.0006789990002289414,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0018079630001466285,
+                                                                    "total": 0.0014897689998178976,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0018079630001466285
+                                                                    "self": 0.0014897689998178976
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.07165920399995684,
+                                                            "total": 0.07897069000000556,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006519400000115638,
+                                                            "self": 0.0006831480000073498,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004405739999810976,
+                                                                    "total": 0.0005036219999965397,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004405739999810976
+                                                                    "self": 0.0005036219999965397
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.06717719300002045,
+                                                                    "total": 0.07441088099994886,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.06717719300002045
+                                                                    "self": 0.07441088099994886
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0033894969999437308,
+                                                                    "total": 0.003373039000052813,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014553430000887602,
+                                                                    "self": 0.0013687670007129782,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0019341539998549706,
+                                                                            "total": 0.002004271999339835,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0019341539998549706
+                                                                            "self": 0.002004271999339835
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 275.8850082439875,
-                                                    "count": 18216,
+                                                    "total": 109.80138764601725,
+                                                    "count": 7263,
                                                     "is_parallel": true,
-                                                    "self": 11.116090181999198,
+                                                    "self": 4.500908722024633,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.932446149989687,
-                                                            "count": 18216,
+                                                            "total": 2.3794146300078864,
+                                                            "count": 7263,
                                                             "is_parallel": true,
-                                                            "self": 5.932446149989687
+                                                            "self": 2.3794146300078864
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 218.4077347730032,
-                                                            "count": 18216,
+                                                            "total": 86.55531314499422,
+                                                            "count": 7263,
                                                             "is_parallel": true,
-                                                            "self": 218.4077347730032
+                                                            "self": 86.55531314499422
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 40.428737138995416,
-                                                            "count": 18216,
+                                                            "total": 16.365751148990512,
+                                                            "count": 7263,
                                                             "is_parallel": true,
-                                                            "self": 7.536981591989729,
+                                                            "self": 3.015981797954737,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 32.89175554700569,
-                                                                    "count": 182160,
+                                                                    "total": 13.349769351035775,
+                                                                    "count": 72630,
                                                                     "is_parallel": true,
-                                                                    "self": 32.89175554700569
+                                                                    "self": 13.349769351035775
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.00018629300006978156,
+                    "total": 0.001425604000360181,
                     "count": 1,
-                    "self": 0.00018629300006978156,
+                    "self": 0.001425604000360181,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 511.1471032080034,
-                                    "count": 485661,
+                                    "total": 204.96596370299812,
+                                    "count": 194646,
                                     "is_parallel": true,
-                                    "self": 11.19884004295352,
+                                    "self": 4.581322357907993,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 280.88084223805004,
-                                            "count": 485661,
+                                            "total": 112.13210191809003,
+                                            "count": 194646,
                                             "is_parallel": true,
-                                            "self": 279.5489161600499,
+                                            "self": 111.92670309709001,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 1.3319260780001514,
-                                                    "count": 4,
+                                                    "total": 0.20539882100001705,
+                                                    "count": 1,
                                                     "is_parallel": true,
-                                                    "self": 1.3319260780001514
+                                                    "self": 0.20539882100001705
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 219.06742092699983,
-                                            "count": 90,
+                                            "total": 88.2525394270001,
+                                            "count": 36,
                                             "is_parallel": true,
-                                            "self": 87.16500623899617,
+                                            "self": 35.320939524002824,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 131.90241468800366,
-                                                    "count": 4587,
+                                                    "total": 52.93159990299728,
+                                                    "count": 1833,
                                                     "is_parallel": true,
-                                                    "self": 131.90241468800366
+                                                    "self": 52.93159990299728
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.25171462399998745,
+                    "total": 0.3117702599997756,
                     "count": 1,
-                    "self": 0.0010647799999787821,
+                    "self": 0.0019030459998248261,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.25064984400000867,
+                            "total": 0.30986721399995076,
                             "count": 1,
-                            "self": 0.25064984400000867
+                            "self": 0.30986721399995076
                         }
                     }
                 }

run_logs/training_status.json

@@ -45,15 +45,33 @@
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
+            },
+            {
+                "steps": 249984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
+                "reward": 26.181818181818183,
+                "creation_time": 1696418968.667711,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
+                ]
+            },
+            {
+                "steps": 279224,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-279224.onnx",
+                "reward": null,
+                "creation_time": 1696419045.9717553,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-279224.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
+            "steps": 279224,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 23.90909090909091,
-            "creation_time": 1696417769.4795413,
+            "reward": null,
+            "creation_time": 1696419045.9717553,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-279224.pt"
             ]
         }
     },