tangwh's picture
First Push
e9290e6 verified
raw
history blame contribute delete
No virus
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9234259724617004,
"min": 0.9234259724617004,
"max": 2.8641409873962402,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8857.501953125,
"min": 8857.501953125,
"max": 29331.66796875,
"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": 13.102073669433594,
"min": 0.3402906060218811,
"max": 13.102073669433594,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2554.904296875,
"min": 66.0163803100586,
"max": 2659.125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06519627982340229,
"min": 0.06255686175712731,
"max": 0.07333011075069068,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26078511929360915,
"min": 0.25022744702850924,
"max": 0.3666505537534534,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19520008870783973,
"min": 0.11657815182230016,
"max": 0.3090468763136396,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7808003548313589,
"min": 0.46631260728920065,
"max": 1.545234381568198,
"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": 25.75,
"min": 3.272727272727273,
"max": 26.136363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1133.0,
"min": 144.0,
"max": 1412.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.75,
"min": 3.272727272727273,
"max": 26.136363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1133.0,
"min": 144.0,
"max": 1412.0,
"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": "1706794703",
"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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706795234"
},
"total": 531.4810592250001,
"count": 1,
"self": 0.7149520939997274,
"children": {
"run_training.setup": {
"total": 0.06429047600022386,
"count": 1,
"self": 0.06429047600022386
},
"TrainerController.start_learning": {
"total": 530.7018166550001,
"count": 1,
"self": 0.7525351229642183,
"children": {
"TrainerController._reset_env": {
"total": 4.472086305000175,
"count": 1,
"self": 4.472086305000175
},
"TrainerController.advance": {
"total": 525.3241750400357,
"count": 18212,
"self": 0.37951603903047726,
"children": {
"env_step": {
"total": 524.9446590010052,
"count": 18212,
"self": 343.29209648897404,
"children": {
"SubprocessEnvManager._take_step": {
"total": 181.28050856906384,
"count": 18212,
"self": 1.8254056670830323,
"children": {
"TorchPolicy.evaluate": {
"total": 179.4551029019808,
"count": 18212,
"self": 179.4551029019808
}
}
},
"workers": {
"total": 0.37205394296734084,
"count": 18212,
"self": 0.0,
"children": {
"worker_root": {
"total": 529.1761781829932,
"count": 18212,
"is_parallel": true,
"self": 258.32781568703695,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009439199000098597,
"count": 1,
"is_parallel": true,
"self": 0.006970667999667057,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024685310004315397,
"count": 10,
"is_parallel": true,
"self": 0.0024685310004315397
}
}
},
"UnityEnvironment.step": {
"total": 0.04803983900001185,
"count": 1,
"is_parallel": true,
"self": 0.0007138379996831645,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004651960002775013,
"count": 1,
"is_parallel": true,
"self": 0.0004651960002775013
},
"communicator.exchange": {
"total": 0.04457644900003288,
"count": 1,
"is_parallel": true,
"self": 0.04457644900003288
},
"steps_from_proto": {
"total": 0.002284356000018306,
"count": 1,
"is_parallel": true,
"self": 0.00045545200009655673,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018289039999217493,
"count": 10,
"is_parallel": true,
"self": 0.0018289039999217493
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 270.8483624959563,
"count": 18211,
"is_parallel": true,
"self": 12.918286717954743,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.589402347007308,
"count": 18211,
"is_parallel": true,
"self": 6.589402347007308
},
"communicator.exchange": {
"total": 210.9396455620231,
"count": 18211,
"is_parallel": true,
"self": 210.9396455620231
},
"steps_from_proto": {
"total": 40.40102786897114,
"count": 18211,
"is_parallel": true,
"self": 7.887491654904352,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.51353621406679,
"count": 182110,
"is_parallel": true,
"self": 32.51353621406679
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001750979999997071,
"count": 1,
"self": 0.0001750979999997071,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 518.3753163017941,
"count": 817795,
"is_parallel": true,
"self": 18.476008731888214,
"children": {
"process_trajectory": {
"total": 288.30443346690663,
"count": 817795,
"is_parallel": true,
"self": 287.09185750190636,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2125759650002692,
"count": 4,
"is_parallel": true,
"self": 1.2125759650002692
}
}
},
"_update_policy": {
"total": 211.59487410299926,
"count": 90,
"is_parallel": true,
"self": 58.93067814999176,
"children": {
"TorchPPOOptimizer.update": {
"total": 152.6641959530075,
"count": 4587,
"is_parallel": true,
"self": 152.6641959530075
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15284508900003857,
"count": 1,
"self": 0.0015717020000920456,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15127338699994652,
"count": 1,
"self": 0.15127338699994652
}
}
}
}
}
}
}