First Push

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2079161d91976a00b1d65c59c1e487e9b90378ac1a8204e754f6fcf4e9917d66
+oid sha256:1c2678baeaa8d47f8306bf996c4cb745f6a765b0bd0a4abff33986f3b60c8868
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57e040dd759bf4c17b75b91584308f049d307249673fefb552f45439a2140cfc
+oid sha256:065229e4efe819ef6b721f632e966ed4502cdd252cf047c09716e24ddecc97b7
 size 3850000

SnowballTarget/SnowballTarget-96800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b40371b170d466c2a6181d642382997d4c02631627783dbce8633b5e168fa79
+size 713

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:247f85612b7d45447d71edcb9d117a8c8428d8bb87df52a0566c8537be314aef
+oid sha256:bfca9e5e40247d67b00983c00a91283a5053a719d56dc247fdd3e0d62e8c3b8f
 size 3849250

SnowballTarget/events.out.tfevents.1741746479.8bba9a8a1fb9.6348.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc1b9791dde63414fcb84fbf63a447f1d0ab1c9a48b4ea6426b58985fa610ad
+size 29104

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": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": 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": 512, "buffer_size": 10240, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -3,8 +3,8 @@ behaviors:
   SnowballTarget:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 128
-      buffer_size: 2048
+      batch_size: 512
+      buffer_size: 10240
       learning_rate: 0.0003
       beta: 0.005
       epsilon: 0.2
@@ -66,7 +66,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: SnowballTarget2
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
 Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.157 seconds
+- Completed reload, in  0.115 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 +42,16 @@ 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: 1.392721 ms
+UnloadTime: 0.630382 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
+GRPC Exception: Status(StatusCode=Cancelled, Detail="CANCELLED"). Disconnecting from trainer.
 Setting up 1 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 2600 frames, [16.0 KB-32.0 KB]: 44 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 +167,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 40
+  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]: 5458 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 2645 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]: 5458 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 2645 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.7 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 +211,13 @@ 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]: 4995 frames, [64.0 KB-128.0 KB]: 463 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1932 frames, [64.0 KB-128.0 KB]: 713 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.0 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]: 5458 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 2645 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +229,13 @@ 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]: 5458 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 2645 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]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 2644 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 +247,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5458 frames
+      Peak usage frame count: [0-1.0 KB]: 2645 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]: 5458 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 2645 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": 0.8420787453651428,
-            "min": 0.8420787453651428,
-            "max": 2.8625736236572266,
-            "count": 20
+            "value": 2.4378271102905273,
+            "min": 2.4378271102905273,
+            "max": 2.890345573425293,
+            "count": 9
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8003.1162109375,
-            "min": 8003.1162109375,
-            "max": 29221.15234375,
-            "count": 20
+            "value": 23169.109375,
+            "min": 23169.109375,
+            "max": 29578.533203125,
+            "count": 9
         },
         "SnowballTarget.Step.mean": {
-            "value": 199984.0,
+            "value": 89984.0,
             "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "max": 89984.0,
+            "count": 9
         },
         "SnowballTarget.Step.sum": {
-            "value": 199984.0,
+            "value": 89984.0,
             "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "max": 89984.0,
+            "count": 9
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 13.228395462036133,
-            "min": 0.5035557150840759,
-            "max": 13.228395462036133,
-            "count": 20
+            "value": 2.4782021045684814,
+            "min": 0.019132515415549278,
+            "max": 2.4782021045684814,
+            "count": 9
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2579.537109375,
-            "min": 97.68980407714844,
-            "max": 2695.68212890625,
-            "count": 20
-        },
-        "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06904638772710528,
-            "min": 0.06166020506894783,
-            "max": 0.07373721250926382,
-            "count": 20
-        },
-        "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2761855509084211,
-            "min": 0.25503849752610275,
-            "max": 0.3686860625463191,
-            "count": 20
-        },
-        "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.20142870871167556,
-            "min": 0.14005450415425003,
-            "max": 0.28048249564918815,
-            "count": 20
-        },
-        "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.8057148348467023,
-            "min": 0.5602180166170001,
-            "max": 1.4024124782459408,
-            "count": 20
-        },
-        "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
-        },
-        "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
-            "count": 20
-        },
-        "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
-        },
-        "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
-            "count": 20
-        },
-        "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
-        },
-        "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828,
-            "count": 20
+            "value": 483.2493896484375,
+            "min": 3.7117080688476562,
+            "max": 483.2493896484375,
+            "count": 9
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 20
+            "count": 9
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
             "value": 8756.0,
             "min": 8756.0,
             "max": 10945.0,
-            "count": 20
+            "count": 9
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 26.09090909090909,
-            "min": 3.977272727272727,
-            "max": 26.472727272727273,
-            "count": 20
+            "value": 10.613636363636363,
+            "min": 2.7954545454545454,
+            "max": 10.613636363636363,
+            "count": 9
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1148.0,
-            "min": 175.0,
-            "max": 1456.0,
-            "count": 20
+            "value": 467.0,
+            "min": 123.0,
+            "max": 553.0,
+            "count": 9
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 26.09090909090909,
-            "min": 3.977272727272727,
-            "max": 26.472727272727273,
-            "count": 20
+            "value": 10.613636363636363,
+            "min": 2.7954545454545454,
+            "max": 10.613636363636363,
+            "count": 9
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1148.0,
-            "min": 175.0,
-            "max": 1456.0,
-            "count": 20
+            "value": 467.0,
+            "min": 123.0,
+            "max": 553.0,
+            "count": 9
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 9
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 9
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.034323636191159794,
+            "min": 0.027952921739779413,
+            "max": 0.03914575736289696,
+            "count": 8
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.034323636191159794,
+            "min": 0.027952921739779413,
+            "max": 0.03914575736289696,
+            "count": 8
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.2925523278613885,
+            "min": 0.09362937640103083,
+            "max": 0.2925523278613885,
+            "count": 8
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.2925523278613885,
+            "min": 0.09362937640103083,
+            "max": 0.2925523278613885,
+            "count": 8
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 0.00017460004180000003,
+            "min": 0.00017460004180000003,
+            "max": 0.0002836320054559999,
+            "count": 8
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 0.00017460004180000003,
+            "min": 0.00017460004180000003,
+            "max": 0.0002836320054559999,
+            "count": 8
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.15820000000000006,
+            "min": 0.15820000000000006,
+            "max": 0.19454400000000008,
+            "count": 8
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.15820000000000006,
+            "min": 0.15820000000000006,
+            "max": 0.19454400000000008,
+            "count": 8
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0029141799999999997,
+            "min": 0.0029141799999999997,
+            "max": 0.0047277456,
+            "count": 8
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0029141799999999997,
+            "min": 0.0029141799999999997,
+            "max": 0.0047277456,
+            "count": 8
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1741745573",
+        "start_time_seconds": "1741746478",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.6.0+cu124",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1741746060"
+        "end_time_seconds": "1741746706"
     },
-    "total": 486.859215643,
+    "total": 227.99882181999988,
     "count": 1,
-    "self": 0.43948498799994695,
+    "self": 0.4766431000000466,
     "children": {
         "run_training.setup": {
-            "total": 0.0404594100000395,
+            "total": 0.022866801999953168,
             "count": 1,
-            "self": 0.0404594100000395
+            "self": 0.022866801999953168
         },
         "TrainerController.start_learning": {
-            "total": 486.37927124500004,
+            "total": 227.49931191799988,
             "count": 1,
-            "self": 0.41491404799393194,
+            "self": 0.2062166350017378,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.8309041170000455,
+                    "total": 2.982515979000027,
                     "count": 1,
-                    "self": 3.8309041170000455
+                    "self": 2.982515979000027
                 },
                 "TrainerController.advance": {
-                    "total": 482.03084730400604,
-                    "count": 18192,
-                    "self": 0.47085410800542604,
+                    "total": 224.30879018899827,
+                    "count": 8816,
+                    "self": 0.22874217300841337,
                     "children": {
                         "env_step": {
-                            "total": 345.7108646989975,
-                            "count": 18192,
-                            "self": 261.47123622300495,
+                            "total": 176.87386586198818,
+                            "count": 8816,
+                            "self": 135.1252220399806,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 83.98766351599568,
-                                    "count": 18192,
-                                    "self": 1.473245178999946,
+                                    "total": 41.616904710996096,
+                                    "count": 8816,
+                                    "self": 0.7266757720044552,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 82.51441833699573,
-                                            "count": 18192,
-                                            "self": 82.51441833699573
+                                            "total": 40.89022893899164,
+                                            "count": 8816,
+                                            "self": 40.89022893899164
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.25196495999688295,
-                                    "count": 18192,
+                                    "total": 0.13173911101148406,
+                                    "count": 8815,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 484.6442554669926,
-                                            "count": 18192,
+                                            "total": 226.69615691500553,
+                                            "count": 8815,
                                             "is_parallel": true,
-                                            "self": 255.88279191199695,
+                                            "self": 108.47960065599136,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0077747810000232676,
+                                                            "total": 0.003010483000025488,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.005096027000035974,
+                                                            "self": 0.000941831000318416,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0026787539999872934,
+                                                                    "total": 0.002068651999707072,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0026787539999872934
+                                                                    "self": 0.002068651999707072
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04313565400002517,
+                                                            "total": 0.07650129599983302,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007152120000455398,
+                                                            "self": 0.0006770369998321257,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00046134999996638726,
+                                                                    "total": 0.0004490060000534868,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00046134999996638726
+                                                                    "self": 0.0004490060000534868
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.039550735000034365,
+                                                                    "total": 0.07299302399997032,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.039550735000034365
+                                                                    "self": 0.07299302399997032
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002408356999978878,
+                                                                    "total": 0.0023822289999770874,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00045056399989107376,
+                                                                    "self": 0.0005039180000494525,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001957793000087804,
+                                                                            "total": 0.0018783109999276348,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001957793000087804
+                                                                            "self": 0.0018783109999276348
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 228.76146355499566,
-                                                    "count": 18191,
+                                                    "total": 118.21655625901417,
+                                                    "count": 8814,
                                                     "is_parallel": true,
-                                                    "self": 11.064770819001865,
+                                                    "self": 5.34642047303123,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 6.291202456993233,
-                                                            "count": 18191,
+                                                            "total": 3.026034669990622,
+                                                            "count": 8814,
                                                             "is_parallel": true,
-                                                            "self": 6.291202456993233
+                                                            "self": 3.026034669990622
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 174.82710657799515,
-                                                            "count": 18191,
+                                                            "total": 91.24543377499299,
+                                                            "count": 8814,
                                                             "is_parallel": true,
-                                                            "self": 174.82710657799515
+                                                            "self": 91.24543377499299
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 36.57838370100541,
-                                                            "count": 18191,
+                                                            "total": 18.598667340999327,
+                                                            "count": 8814,
                                                             "is_parallel": true,
-                                                            "self": 6.7102560469925265,
+                                                            "self": 3.446608240046544,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 29.86812765401288,
-                                                                    "count": 181910,
+                                                                    "total": 15.152059100952783,
+                                                                    "count": 88140,
                                                                     "is_parallel": true,
-                                                                    "self": 29.86812765401288
+                                                                    "self": 15.152059100952783
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 135.8491284970031,
-                            "count": 18192,
-                            "self": 0.5000056670073718,
+                            "total": 47.20618215400168,
+                            "count": 8815,
+                            "self": 0.2406024040083139,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 30.252582493994623,
-                                    "count": 18192,
-                                    "self": 29.529683940994573,
+                                    "total": 15.71958198699349,
+                                    "count": 8815,
+                                    "self": 15.58294844799343,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.72289855300005,
-                                            "count": 4,
-                                            "self": 0.72289855300005
+                                            "total": 0.1366335390000586,
+                                            "count": 1,
+                                            "self": 0.1366335390000586
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 105.09654033600111,
-                                    "count": 90,
-                                    "self": 42.291469808000556,
+                                    "total": 31.245997762999878,
+                                    "count": 9,
+                                    "self": 21.636983077997684,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 62.805070528000556,
-                                            "count": 4587,
-                                            "self": 62.805070528000556
+                                            "total": 9.609014685002194,
+                                            "count": 549,
+                                            "self": 9.609014685002194
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.2210000477352878e-06,
+                    "total": 1.2219998097862117e-06,
                     "count": 1,
-                    "self": 1.2210000477352878e-06
+                    "self": 1.2219998097862117e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.10260455499997079,
+                    "total": 0.001787893000027907,
                     "count": 1,
-                    "self": 0.0009255879999727767,
+                    "self": 2.570699984971725e-05,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.10167896699999801,
+                            "total": 0.0017621860001781897,
                             "count": 1,
-                            "self": 0.10167896699999801
+                            "self": 0.0017621860001781897
                         }
                     }
                 }

run_logs/training_status.json

@@ -3,59 +3,14 @@
         "checkpoints": [
             {
                 "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 16.09090909090909,
-                "creation_time": 1741745701.7511792,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 8.030303030303031,
+                "creation_time": 1741746596.159259,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
-                ]
-            },
-            {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 24.636363636363637,
-                "creation_time": 1741745817.7127948,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
-                ]
-            },
-            {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 27.0,
-                "creation_time": 1741745945.7596734,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
-                ]
-            },
-            {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.90909090909091,
-                "creation_time": 1741746059.5441957,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
-                ]
-            },
-            {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.90909090909091,
-                "creation_time": 1741746059.6598566,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             }
-        ],
-        "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 25.90909090909091,
-            "creation_time": 1741746059.6598566,
-            "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
-            ]
-        }
+        ]
     },
     "metadata": {
         "stats_format_version": "0.3.0",