First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6a7ac1ceee5528c7d5516bfd359c8f82157ca22b22ed20fb6605e2bd523ce9f
-size 649740
+oid sha256:03561aa37d62a6fbdb553d9a5f0d634b36b154b8d827411b1162036e2ac29bda
+size 650646

SnowballTarget/SnowballTarget-0.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6a7ac1ceee5528c7d5516bfd359c8f82157ca22b22ed20fb6605e2bd523ce9f
+oid sha256:5e74dd491c9da3115be193d1000ed52867fe231d9092bceabbd83579d5dcece5
 size 649740

SnowballTarget/SnowballTarget-0.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bc45d770b512913a59e694c03bd5c5a264633ebc29566300ca66d4c3562c473
+oid sha256:e5a48705a85367c39e07094d98c1872db293b9c898bb830cffcf29c4165d83fe
 size 1286148

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b6ad823a7062cf31deff8cf6c8a52613d8e7cb76c3b2132238f3e9ffd0300a
+size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68849b99fd31831b96e2b83030047bfa09225281ba9de45fd2a513fba1f830ed
+size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03561aa37d62a6fbdb553d9a5f0d634b36b154b8d827411b1162036e2ac29bda
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b7cbe205e714856ebadef3fc1d9b05c0615f304768ca4cfe2cea8c7687c823
+size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03561aa37d62a6fbdb553d9a5f0d634b36b154b8d827411b1162036e2ac29bda
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c2c523c4d8a9a7c21f6b894071abc3c1e7574f0d5cba038e19895c51797e997
+size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd05197fed6e6f34375fbf86fdec64a4a867ca5b3179ce713b300381de1162f4
+size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b01b0b7936079a684cb16c77ff0cb4c3522d1db1d5a1f9c9eb21782f5a5aef0
+size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:500e51cfa8b45ef575519d29f448d4aa4835d8e8d32e2886c6a7059277867d2e
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be29f951b2343e592c750f48d2e104784c4bf6c2b57a55732bbec4c74e209c68
+size 3850000

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a0be8eda790704a9f9db41c4cdcaca3848de2944141cb9ea53365f45d28298
-size 1285986
+oid sha256:f2fabc9c5fbfecc9b87a1d81b8332e4aefdfdac670ed6352effa56a48b79969f
+size 3849250

SnowballTarget/events.out.tfevents.1714068223.beb444bef870.3399.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67b8ddccbc28f70a054b682cf06ee5261227c396356dbc4c823e0d449236d11
+size 1114

SnowballTarget/events.out.tfevents.1714068248.beb444bef870.3556.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a1627d5bd031bcb4ff7f9a7759c84c579d58456eb52356006c81b1f70fc25c
+size 28493

run_logs/Player-0.log

@@ -2,7 +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'
-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
@@ -32,7 +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  0.139 seconds
+- Completed reload, in  0.082 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)
@@ -43,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.885862 ms
+UnloadTime: 0.633190 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.
@@ -51,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5371 frames, [16.0 KB-32.0 KB]: 91 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
@@ -79,7 +78,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 2.8 KB
+      Peak Allocated Bytes 3.6 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
@@ -167,23 +166,23 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 3
+  Peak main deferred allocation count 42
     [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: [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5463 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 20.6 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 6.7 MB
+      Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 1 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 1.8 MB
-      Peak Large allocation bytes 0 B
+      Peak Allocated memory 17.8 MB
+      Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -196,7 +195,7 @@ Memory Statistics:
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
   Initial Block Size 2.0 MB
-  Used Block Count 1
+  Used Block Count 2
   Overflow Count (too large) 0
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -211,13 +210,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4683 frames, [64.0 KB-128.0 KB]: 780 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 KB
+      Peak Allocated memory 66.4 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5463 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -229,13 +228,13 @@ 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]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5463 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.5 MB
+      Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5462 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
@@ -247,13 +246,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 1 frames
+      Peak usage frame count: [0-1.0 KB]: 5463 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]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5463 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -1,8 +1,154 @@
 {
     "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 1.0807324647903442,
+            "min": 1.0807324647903442,
+            "max": 2.8461053371429443,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 10354.498046875,
+            "min": 10354.498046875,
+            "max": 29146.96484375,
+            "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": 12.872466087341309,
+            "min": 0.2798191010951996,
+            "max": 12.872466087341309,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2510.130859375,
+            "min": 54.28490447998047,
+            "max": 2598.914306640625,
+            "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.Losses.PolicyLoss.mean": {
+            "value": 0.06713295188013695,
+            "min": 0.06332136134105716,
+            "max": 0.07353326213356637,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.2685318075205478,
+            "min": 0.25436817821316127,
+            "max": 0.36095829919855427,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.18941276071264462,
+            "min": 0.11052791246295195,
+            "max": 0.28012132253132616,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7576510428505785,
+            "min": 0.4421116498518078,
+            "max": 1.4006066126566308,
+            "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.CumulativeReward.mean": {
+            "value": 25.25,
+            "min": 3.022727272727273,
+            "max": 25.30909090909091,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1111.0,
+            "min": 133.0,
+            "max": 1392.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.25,
+            "min": 3.022727272727273,
+            "max": 25.30909090909091,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1111.0,
+            "min": 133.0,
+            "max": 1392.0,
+            "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": "1713720998",
+        "start_time_seconds": "1714068247",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
         "mlagents_version": "1.1.0.dev0",
@@ -10,36 +156,218 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.2.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1713721002"
+        "end_time_seconds": "1714068668"
     },
-    "total": 3.938492743999973,
+    "total": 420.715021073,
     "count": 1,
-    "self": 0.4859255750000102,
+    "self": 0.4777426770000375,
     "children": {
         "run_training.setup": {
-            "total": 0.07588937799994255,
+            "total": 0.04971012199996494,
             "count": 1,
-            "self": 0.07588937799994255
+            "self": 0.04971012199996494
         },
         "TrainerController.start_learning": {
-            "total": 3.37667779100002,
+            "total": 420.187568274,
             "count": 1,
-            "self": 8.873500007666735e-05,
+            "self": 0.5354431570043516,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.7290911339999866,
+                    "total": 1.9202147020000666,
                     "count": 1,
-                    "self": 2.7290911339999866
+                    "self": 1.9202147020000666
+                },
+                "TrainerController.advance": {
+                    "total": 417.5849732109957,
+                    "count": 18208,
+                    "self": 0.24664360600365853,
+                    "children": {
+                        "env_step": {
+                            "total": 417.33832960499205,
+                            "count": 18208,
+                            "self": 268.5468170329914,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 148.52372747999232,
+                                    "count": 18208,
+                                    "self": 1.3610523449710854,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 147.16267513502123,
+                                            "count": 18208,
+                                            "self": 147.16267513502123
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.2677850920083529,
+                                    "count": 18208,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 419.10637281200604,
+                                            "count": 18208,
+                                            "is_parallel": true,
+                                            "self": 208.58721213401316,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0022132899999860456,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005881309999722362,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0016251590000138094,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0016251590000138094
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.036491395999973975,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006436549999762065,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00038819999997485866,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00038819999997485866
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03356306400007725,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03356306400007725
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.001896476999945662,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00037919599992619624,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0015172810000194659,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0015172810000194659
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 210.5191606779929,
+                                                    "count": 18207,
+                                                    "is_parallel": true,
+                                                    "self": 10.005351809016133,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.179817442999479,
+                                                            "count": 18207,
+                                                            "is_parallel": true,
+                                                            "self": 5.179817442999479
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 163.3224772199834,
+                                                            "count": 18207,
+                                                            "is_parallel": true,
+                                                            "self": 163.3224772199834
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 32.011514205993876,
+                                                            "count": 18207,
+                                                            "is_parallel": true,
+                                                            "self": 5.878366111971445,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 26.13314809402243,
+                                                                    "count": 182070,
+                                                                    "is_parallel": true,
+                                                                    "self": 26.13314809402243
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0001329990000158432,
+                    "count": 1,
+                    "self": 0.0001329990000158432,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 412.45401418296944,
+                                    "count": 665045,
+                                    "is_parallel": true,
+                                    "self": 13.075854123977479,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 227.66651940699182,
+                                            "count": 665045,
+                                            "is_parallel": true,
+                                            "self": 227.00325328399163,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.6632661230001986,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.6632661230001986
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 171.71164065200014,
+                                            "count": 90,
+                                            "is_parallel": true,
+                                            "self": 50.22559865800213,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 121.48604199399801,
+                                                    "count": 4587,
+                                                    "is_parallel": true,
+                                                    "self": 121.48604199399801
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.6474979219999568,
+                    "total": 0.14680420499985303,
                     "count": 1,
-                    "self": 0.0009898969999539986,
+                    "self": 0.0016170659998806514,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.6465080250000028,
+                            "total": 0.14518713899997238,
                             "count": 1,
-                            "self": 0.6465080250000028
+                            "self": 0.14518713899997238
                         }
                     }
                 }

run_logs/training_status.json

@@ -10,19 +10,64 @@
                 "steps": 0,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-0.onnx",
                 "reward": null,
-                "creation_time": 1713721001.83264,
+                "creation_time": 1714068226.1064408,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-0.pt"
                 ]
+            },
+            {
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 11.181818181818182,
+                "creation_time": 1714068355.0204248,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 19.636363636363637,
+                "creation_time": 1714068460.7090538,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 24.272727272727273,
+                "creation_time": 1714068564.2146447,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.181818181818183,
+                "creation_time": 1714068667.708035,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 25.181818181818183,
+                "creation_time": 1714068667.8731527,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 0,
+            "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": null,
-            "creation_time": 1713721001.83264,
+            "reward": 25.181818181818183,
+            "creation_time": 1714068667.8731527,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-0.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     }