First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d3c1b10eea4f24ec233406ea91ee17e5a784a40eb1dd366d5ec187df18e0026
-size 649740
+oid sha256:e29c4374cef7edfdfa62b22bd8930f5ed16cb463b529c11d57701d630a13987a
+size 650646

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be48abe216ba90c24f20e121d4289c002597de12a869898730986c98715e81bc
-size 1285986
+oid sha256:247f85612b7d45447d71edcb9d117a8c8428d8bb87df52a0566c8537be314aef
+size 3849250

config.json

@@ -1 +1 @@
-{"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}
+{"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}

configuration.yaml

@@ -3,8 +3,8 @@ behaviors:
   SnowballTarget:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 512
-      buffer_size: 10240
+      batch_size: 128
+      buffer_size: 2048
       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: SnowballTarget2
+  run_id: SnowballTarget1
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -2,6 +2,9 @@ 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
@@ -31,7 +34,7 @@ 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  0.092 seconds
+- Completed reload, in  0.157 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -42,7 +45,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.759224 ms
+UnloadTime: 1.392721 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.
@@ -50,7 +53,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 204 frames, [16.0 KB-32.0 KB]: 3 frames, [2.0 MB-4.0 MB]: 1 frames
+      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
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -166,22 +169,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 32
+  Peak main deferred allocation count 40
     [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]: 208 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.2 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]: 208 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.8 MB
+      Peak Allocated memory 17.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -210,13 +213,13 @@ 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]: 191 frames, [64.0 KB-128.0 KB]: 17 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4995 frames, [64.0 KB-128.0 KB]: 463 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 KB
+      Peak Allocated memory 66.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 208 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -228,13 +231,13 @@ 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]: 208 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5458 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]: 207 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5457 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
@@ -246,13 +249,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 208 frames
+      Peak usage frame count: [0-1.0 KB]: 5458 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]: 208 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -1,68 +1,214 @@
 {
     "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.8420787453651428,
+            "min": 0.8420787453651428,
+            "max": 2.8625736236572266,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 8003.1162109375,
+            "min": 8003.1162109375,
+            "max": 29221.15234375,
+            "count": 20
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.228395462036133,
+            "min": 0.5035557150840759,
+            "max": 13.228395462036133,
+            "count": 20
+        },
+        "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
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.09090909090909,
+            "min": 3.977272727272727,
+            "max": 26.472727272727273,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1148.0,
+            "min": 175.0,
+            "max": 1456.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.09090909090909,
+            "min": 3.977272727272727,
+            "max": 26.472727272727273,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1148.0,
+            "min": 175.0,
+            "max": 1456.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1741746368",
+        "start_time_seconds": "1741745573",
         "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=SnowballTarget2 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1741746387"
+        "end_time_seconds": "1741746060"
     },
-    "total": 18.975267084000052,
+    "total": 486.859215643,
     "count": 1,
-    "self": 0.4642486770001142,
+    "self": 0.43948498799994695,
     "children": {
         "run_training.setup": {
-            "total": 0.027944295999986934,
+            "total": 0.0404594100000395,
             "count": 1,
-            "self": 0.027944295999986934
+            "self": 0.0404594100000395
         },
         "TrainerController.start_learning": {
-            "total": 18.48307411099995,
+            "total": 486.37927124500004,
             "count": 1,
-            "self": 0.01692610199665978,
+            "self": 0.41491404799393194,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.2062937809998857,
+                    "total": 3.8309041170000455,
                     "count": 1,
-                    "self": 2.2062937809998857
+                    "self": 3.8309041170000455
                 },
                 "TrainerController.advance": {
-                    "total": 15.985262898003384,
-                    "count": 692,
-                    "self": 0.018765200003826976,
+                    "total": 482.03084730400604,
+                    "count": 18192,
+                    "self": 0.47085410800542604,
                     "children": {
                         "env_step": {
-                            "total": 14.838615273000869,
-                            "count": 692,
-                            "self": 11.12357527100221,
+                            "total": 345.7108646989975,
+                            "count": 18192,
+                            "self": 261.47123622300495,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 3.7056855230000565,
-                                    "count": 692,
-                                    "self": 0.06572072400103934,
+                                    "total": 83.98766351599568,
+                                    "count": 18192,
+                                    "self": 1.473245178999946,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 3.639964798999017,
-                                            "count": 692,
-                                            "self": 3.639964798999017
+                                            "total": 82.51441833699573,
+                                            "count": 18192,
+                                            "self": 82.51441833699573
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.009354478998602644,
-                                    "count": 691,
+                                    "total": 0.25196495999688295,
+                                    "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 18.14547060300015,
-                                            "count": 691,
+                                            "total": 484.6442554669926,
+                                            "count": 18192,
                                             "is_parallel": true,
-                                            "self": 8.53648198700239,
+                                            "self": 255.88279191199695,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -71,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0031006869999146147,
+                                                            "total": 0.0077747810000232676,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000860624999859283,
+                                                            "self": 0.005096027000035974,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0022400620000553317,
+                                                                    "total": 0.0026787539999872934,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0022400620000553317
+                                                                    "self": 0.0026787539999872934
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.046287394000046334,
+                                                            "total": 0.04313565400002517,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006919589998233278,
+                                                            "self": 0.0007152120000455398,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00044526500005304115,
+                                                                    "total": 0.00046134999996638726,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00044526500005304115
+                                                                    "self": 0.00046134999996638726
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.042899765000129264,
+                                                                    "total": 0.039550735000034365,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.042899765000129264
+                                                                    "self": 0.039550735000034365
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0022504050000407005,
+                                                                    "total": 0.002408356999978878,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004915099998470396,
+                                                                    "self": 0.00045056399989107376,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001758895000193661,
+                                                                            "total": 0.001957793000087804,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001758895000193661
+                                                                            "self": 0.001957793000087804
                                                                         }
                                                                     }
                                                                 }
@@ -121,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 9.60898861599776,
-                                                    "count": 690,
+                                                    "total": 228.76146355499566,
+                                                    "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 0.44187826600000335,
+                                                    "self": 11.064770819001865,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.2308547079987875,
-                                                            "count": 690,
+                                                            "total": 6.291202456993233,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.2308547079987875
+                                                            "self": 6.291202456993233
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 7.469084829001758,
-                                                            "count": 690,
+                                                            "total": 174.82710657799515,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 7.469084829001758
+                                                            "self": 174.82710657799515
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 1.4671708129972103,
-                                                            "count": 690,
+                                                            "total": 36.57838370100541,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.27933691499106317,
+                                                            "self": 6.7102560469925265,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 1.1878338980061471,
-                                                                    "count": 6900,
+                                                                    "total": 29.86812765401288,
+                                                                    "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 1.1878338980061471
+                                                                    "self": 29.86812765401288
                                                                 }
                                                             }
                                                         }
@@ -161,33 +307,52 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1.1278824249986883,
-                            "count": 691,
-                            "self": 0.0195556949956881,
+                            "total": 135.8491284970031,
+                            "count": 18192,
+                            "self": 0.5000056670073718,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 1.1083267300030002,
-                                    "count": 691,
-                                    "self": 1.1083267300030002
+                                    "total": 30.252582493994623,
+                                    "count": 18192,
+                                    "self": 29.529683940994573,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.72289855300005,
+                                            "count": 4,
+                                            "self": 0.72289855300005
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 105.09654033600111,
+                                    "count": 90,
+                                    "self": 42.291469808000556,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 62.805070528000556,
+                                            "count": 4587,
+                                            "self": 62.805070528000556
+                                        }
+                                    }
                                 }
                             }
                         }
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.3310000213095918e-06,
+                    "total": 1.2210000477352878e-06,
                     "count": 1,
-                    "self": 1.3310000213095918e-06
+                    "self": 1.2210000477352878e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.2745899989999998,
+                    "total": 0.10260455499997079,
                     "count": 1,
-                    "self": 0.0012880399999630754,
+                    "self": 0.0009255879999727767,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.27330195900003673,
+                            "total": 0.10167896699999801,
                             "count": 1,
-                            "self": 0.27330195900003673
+                            "self": 0.10167896699999801
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,58 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 7304,
-                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-7304.onnx",
-                "reward": 2.272727272727273,
-                "creation_time": 1741746386.632966,
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 16.09090909090909,
+                "creation_time": 1741745701.7511792,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-7304.pt"
+                    "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"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 7304,
-            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
-            "reward": 2.272727272727273,
-            "creation_time": 1741746386.632966,
+            "steps": 200112,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 25.90909090909091,
+            "creation_time": 1741746059.6598566,
             "auxillary_file_paths": [
-                "results/SnowballTarget2/SnowballTarget/SnowballTarget-7304.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },