gaiamolinaro's picture
First Push
5554745
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7007917761802673,
"min": 0.7007917761802673,
"max": 2.8717386722564697,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6691.16015625,
"min": 6691.16015625,
"max": 29409.4765625,
"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": 12.876601219177246,
"min": 0.40219616889953613,
"max": 12.876601219177246,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2510.937255859375,
"min": 78.02605438232422,
"max": 2598.562744140625,
"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": 0.07223271085618477,
"min": 0.06598695664091364,
"max": 0.0743950203771009,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28893084342473907,
"min": 0.27003206845427696,
"max": 0.3719751018855045,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19392475964245842,
"min": 0.10081676035370751,
"max": 0.289689290538138,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7756990385698337,
"min": 0.40326704141483005,
"max": 1.3283781318687924,
"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": 25.068181818181817,
"min": 3.1136363636363638,
"max": 25.436363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1103.0,
"min": 137.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.068181818181817,
"min": 3.1136363636363638,
"max": 25.436363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1103.0,
"min": 137.0,
"max": 1399.0,
"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": "1687659793",
"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": "1687660241"
},
"total": 447.80469168800005,
"count": 1,
"self": 0.38690302700001666,
"children": {
"run_training.setup": {
"total": 0.06506019899998705,
"count": 1,
"self": 0.06506019899998705
},
"TrainerController.start_learning": {
"total": 447.352728462,
"count": 1,
"self": 0.49597082900442047,
"children": {
"TrainerController._reset_env": {
"total": 5.087199492000025,
"count": 1,
"self": 5.087199492000025
},
"TrainerController.advance": {
"total": 441.63778586899565,
"count": 18200,
"self": 0.24821400200028165,
"children": {
"env_step": {
"total": 441.38957186699537,
"count": 18200,
"self": 319.8957153510032,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.24642155499748,
"count": 18200,
"self": 1.7059118869854615,
"children": {
"TorchPolicy.evaluate": {
"total": 119.54050966801202,
"count": 18200,
"self": 119.54050966801202
}
}
},
"workers": {
"total": 0.2474349609946671,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 445.9628809859982,
"count": 18200,
"is_parallel": true,
"self": 210.70939085999117,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0066199240000059945,
"count": 1,
"is_parallel": true,
"self": 0.004465588000044818,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021543359999611766,
"count": 10,
"is_parallel": true,
"self": 0.0021543359999611766
}
}
},
"UnityEnvironment.step": {
"total": 0.060044651999987764,
"count": 1,
"is_parallel": true,
"self": 0.0007282120000127179,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039773299999978917,
"count": 1,
"is_parallel": true,
"self": 0.00039773299999978917
},
"communicator.exchange": {
"total": 0.05676869699999543,
"count": 1,
"is_parallel": true,
"self": 0.05676869699999543
},
"steps_from_proto": {
"total": 0.0021500099999798294,
"count": 1,
"is_parallel": true,
"self": 0.0003849809999678655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001765029000011964,
"count": 10,
"is_parallel": true,
"self": 0.001765029000011964
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 235.25349012600702,
"count": 18199,
"is_parallel": true,
"self": 9.955133967004372,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.934350297004357,
"count": 18199,
"is_parallel": true,
"self": 4.934350297004357
},
"communicator.exchange": {
"total": 187.69404045100617,
"count": 18199,
"is_parallel": true,
"self": 187.69404045100617
},
"steps_from_proto": {
"total": 32.66996541099212,
"count": 18199,
"is_parallel": true,
"self": 5.841257226001346,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.828708184990774,
"count": 181990,
"is_parallel": true,
"self": 26.828708184990774
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014083099995332304,
"count": 1,
"self": 0.00014083099995332304,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 438.36848428897304,
"count": 414739,
"is_parallel": true,
"self": 9.07414454191894,
"children": {
"process_trajectory": {
"total": 239.93524379605446,
"count": 414739,
"is_parallel": true,
"self": 238.8563409450545,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0789028509999525,
"count": 4,
"is_parallel": true,
"self": 1.0789028509999525
}
}
},
"_update_policy": {
"total": 189.35909595099963,
"count": 90,
"is_parallel": true,
"self": 70.67847903499478,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.68061691600485,
"count": 4587,
"is_parallel": true,
"self": 118.68061691600485
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1316314409999677,
"count": 1,
"self": 0.0008053649999055779,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13082607600006213,
"count": 1,
"self": 0.13082607600006213
}
}
}
}
}
}
}