chencjiajy's picture
First Push
938282d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.081818103790283,
"min": 2.081818103790283,
"max": 2.890320062637329,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 19945.900390625,
"min": 19945.900390625,
"max": 29631.5625,
"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": 7.1449198722839355,
"min": 0.20660436153411865,
"max": 7.1449198722839355,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1393.2593994140625,
"min": 40.08124542236328,
"max": 1402.5081787109375,
"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": 19.15909090909091,
"min": 2.840909090909091,
"max": 19.15909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 843.0,
"min": 125.0,
"max": 993.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 19.15909090909091,
"min": 2.840909090909091,
"max": 19.15909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 843.0,
"min": 125.0,
"max": 993.0,
"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
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07138944182603155,
"min": 0.06741365752171077,
"max": 0.07545099694132659,
"count": 19
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.07138944182603155,
"min": 0.06741365752171077,
"max": 0.07545099694132659,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.24113609991967677,
"min": 0.08754954038164284,
"max": 0.27189324189115455,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.24113609991967677,
"min": 0.08754954038164284,
"max": 0.27189324189115455,
"count": 19
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.488097503999997e-06,
"min": 7.488097503999997e-06,
"max": 0.000284688005104,
"count": 19
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 7.488097503999997e-06,
"min": 7.488097503999997e-06,
"max": 0.000284688005104,
"count": 19
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10249599999999999,
"min": 0.10249599999999999,
"max": 0.19489599999999999,
"count": 19
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10249599999999999,
"min": 0.10249599999999999,
"max": 0.19489599999999999,
"count": 19
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001345503999999999,
"min": 0.0001345503999999999,
"max": 0.0047453104,
"count": 19
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0001345503999999999,
"min": 0.0001345503999999999,
"max": 0.0047453104,
"count": 19
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1687782055",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1687782806"
},
"total": 751.003054222,
"count": 1,
"self": 0.48209105699993415,
"children": {
"run_training.setup": {
"total": 0.04352865200002043,
"count": 1,
"self": 0.04352865200002043
},
"TrainerController.start_learning": {
"total": 750.4774345129999,
"count": 1,
"self": 0.6113167429984969,
"children": {
"TrainerController._reset_env": {
"total": 4.264184330999967,
"count": 1,
"self": 4.264184330999967
},
"TrainerController.advance": {
"total": 745.4550483160015,
"count": 18211,
"self": 0.3136914080075712,
"children": {
"env_step": {
"total": 745.1413569079939,
"count": 18211,
"self": 623.0485703049715,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.78118716900661,
"count": 18211,
"self": 2.1840081600121835,
"children": {
"TorchPolicy.evaluate": {
"total": 119.59717900899443,
"count": 18211,
"self": 119.59717900899443
}
}
},
"workers": {
"total": 0.3115994340157613,
"count": 18211,
"self": 0.0,
"children": {
"worker_root": {
"total": 748.6590063300098,
"count": 18211,
"is_parallel": true,
"self": 480.8584148119985,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005324081000026126,
"count": 1,
"is_parallel": true,
"self": 0.0038750689998892085,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014490120001369178,
"count": 10,
"is_parallel": true,
"self": 0.0014490120001369178
}
}
},
"UnityEnvironment.step": {
"total": 0.03890719300000001,
"count": 1,
"is_parallel": true,
"self": 0.0007034730000441414,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003925469999899178,
"count": 1,
"is_parallel": true,
"self": 0.0003925469999899178
},
"communicator.exchange": {
"total": 0.035437652999974034,
"count": 1,
"is_parallel": true,
"self": 0.035437652999974034
},
"steps_from_proto": {
"total": 0.002373519999991913,
"count": 1,
"is_parallel": true,
"self": 0.0004230440001151692,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001950475999876744,
"count": 10,
"is_parallel": true,
"self": 0.001950475999876744
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 267.8005915180113,
"count": 18210,
"is_parallel": true,
"self": 11.286286609018191,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.702698314992745,
"count": 18210,
"is_parallel": true,
"self": 5.702698314992745
},
"communicator.exchange": {
"total": 212.6485966630019,
"count": 18210,
"is_parallel": true,
"self": 212.6485966630019
},
"steps_from_proto": {
"total": 38.16300993099844,
"count": 18210,
"is_parallel": true,
"self": 7.027499449044228,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.135510481954213,
"count": 182100,
"is_parallel": true,
"self": 31.135510481954213
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013075199990453257,
"count": 1,
"self": 0.00013075199990453257,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 739.5798110090517,
"count": 682896,
"is_parallel": true,
"self": 15.338020008004037,
"children": {
"process_trajectory": {
"total": 365.7175372800477,
"count": 682896,
"is_parallel": true,
"self": 364.4045846020476,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3129526780001015,
"count": 4,
"is_parallel": true,
"self": 1.3129526780001015
}
}
},
"_update_policy": {
"total": 358.524253721,
"count": 19,
"is_parallel": true,
"self": 187.40280251000172,
"children": {
"TorchPPOOptimizer.update": {
"total": 171.12145121099826,
"count": 15130,
"is_parallel": true,
"self": 171.12145121099826
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14675437100004274,
"count": 1,
"self": 0.0009781720000319183,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14577619900001082,
"count": 1,
"self": 0.14577619900001082
}
}
}
}
}
}
}