binhpham's picture
First Push
51688fc verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1745225191116333,
"min": 1.1553934812545776,
"max": 2.875142812728882,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11162.662109375,
"min": 11162.662109375,
"max": 29349.458984375,
"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": 12.326047897338867,
"min": 0.12816299498081207,
"max": 12.326047897338867,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2403.579345703125,
"min": 24.86362075805664,
"max": 2463.56591796875,
"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": 25.34090909090909,
"min": 3.5,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 154.0,
"max": 1383.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.5,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 154.0,
"max": 1383.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06742046634420096,
"min": 0.061809752128907595,
"max": 0.07929553746580971,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.13484093268840192,
"min": 0.12361950425781519,
"max": 0.23788661239742914,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1991138804484816,
"min": 0.11531118519573218,
"max": 0.2868971896960455,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3982277608969632,
"min": 0.23062237039146435,
"max": 0.823885958276543,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.072009785600001e-05,
"min": 1.072009785600001e-05,
"max": 0.00048372000325600005,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.144019571200002e-05,
"min": 2.144019571200002e-05,
"max": 0.0012366600526680005,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10214399999999998,
"min": 0.10214399999999998,
"max": 0.19674400000000003,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.20428799999999997,
"min": 0.20428799999999997,
"max": 0.5473319999999999,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00011698560000000007,
"min": 0.00011698560000000007,
"max": 0.004837525599999998,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00023397120000000015,
"min": 0.00023397120000000015,
"max": 0.0123718668,
"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": "1743599478",
"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=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": "1743599920"
},
"total": 441.9864201680001,
"count": 1,
"self": 0.4411293010002737,
"children": {
"run_training.setup": {
"total": 0.02298613299990393,
"count": 1,
"self": 0.02298613299990393
},
"TrainerController.start_learning": {
"total": 441.52230473399993,
"count": 1,
"self": 0.37350977400251395,
"children": {
"TrainerController._reset_env": {
"total": 3.133184730000039,
"count": 1,
"self": 3.133184730000039
},
"TrainerController.advance": {
"total": 437.92832028199734,
"count": 18192,
"self": 0.38631594197624963,
"children": {
"env_step": {
"total": 311.3511103340029,
"count": 18192,
"self": 236.40219222600547,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.72669086299311,
"count": 18192,
"self": 1.3334148199879792,
"children": {
"TorchPolicy.evaluate": {
"total": 73.39327604300513,
"count": 18192,
"self": 73.39327604300513
}
}
},
"workers": {
"total": 0.22222724500431923,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 440.07289683700276,
"count": 18192,
"is_parallel": true,
"self": 232.71911328299586,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006555145999982415,
"count": 1,
"is_parallel": true,
"self": 0.004968622999854233,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015865230001281816,
"count": 10,
"is_parallel": true,
"self": 0.0015865230001281816
}
}
},
"UnityEnvironment.step": {
"total": 0.06061384800000269,
"count": 1,
"is_parallel": true,
"self": 0.000574397000150384,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037624399999458547,
"count": 1,
"is_parallel": true,
"self": 0.00037624399999458547
},
"communicator.exchange": {
"total": 0.05790966999995817,
"count": 1,
"is_parallel": true,
"self": 0.05790966999995817
},
"steps_from_proto": {
"total": 0.001753536999899552,
"count": 1,
"is_parallel": true,
"self": 0.00032146900014140556,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014320679997581465,
"count": 10,
"is_parallel": true,
"self": 0.0014320679997581465
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.3537835540069,
"count": 18191,
"is_parallel": true,
"self": 10.041369670990548,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.408120060001693,
"count": 18191,
"is_parallel": true,
"self": 5.408120060001693
},
"communicator.exchange": {
"total": 159.42987283799994,
"count": 18191,
"is_parallel": true,
"self": 159.42987283799994
},
"steps_from_proto": {
"total": 32.47442098501472,
"count": 18191,
"is_parallel": true,
"self": 5.996444214018652,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.477976770996065,
"count": 181910,
"is_parallel": true,
"self": 26.477976770996065
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 126.1908940060182,
"count": 18192,
"self": 0.4638054240189149,
"children": {
"process_trajectory": {
"total": 28.029551129999845,
"count": 18192,
"self": 27.58940997499974,
"children": {
"RLTrainer._checkpoint": {
"total": 0.44014115500010575,
"count": 4,
"self": 0.44014115500010575
}
}
},
"_update_policy": {
"total": 97.69753745199944,
"count": 45,
"self": 39.476598018996924,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.22093943300251,
"count": 4587,
"self": 58.22093943300251
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.829999049135949e-07,
"count": 1,
"self": 7.829999049135949e-07
},
"TrainerController._save_models": {
"total": 0.08728916500012929,
"count": 1,
"self": 0.0010089910001624958,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08628017399996679,
"count": 1,
"self": 0.08628017399996679
}
}
}
}
}
}
}