andyv237's picture
First Push
9ced938 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.6685758829116821,
"min": 1.6685758829116821,
"max": 2.883042573928833,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 15858.1455078125,
"min": 15858.1455078125,
"max": 29430.09765625,
"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": 9.110578536987305,
"min": 0.24262823164463043,
"max": 9.110578536987305,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1776.562744140625,
"min": 47.06987762451172,
"max": 1807.24365234375,
"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": 19.363636363636363,
"min": 3.090909090909091,
"max": 19.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 852.0,
"min": 136.0,
"max": 1035.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 19.363636363636363,
"min": 3.090909090909091,
"max": 19.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 852.0,
"min": 136.0,
"max": 1035.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.03406004786180953,
"min": 0.023869980389387518,
"max": 0.03836621155450201,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.06812009572361906,
"min": 0.05473207745732604,
"max": 0.11509863466350603,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.3105844290306171,
"min": 0.1173855384501318,
"max": 0.3105844290306171,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6211688580612342,
"min": 0.2347710769002636,
"max": 0.8737930506467819,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 6.432097856000005e-06,
"min": 6.432097856000005e-06,
"max": 0.000290232003256,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.286419571200001e-05,
"min": 1.286419571200001e-05,
"max": 0.0007419960526679999,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10214400000000001,
"min": 0.10214400000000001,
"max": 0.19674400000000003,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.20428800000000003,
"min": 0.20428800000000003,
"max": 0.547332,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00011698560000000009,
"min": 0.00011698560000000009,
"max": 0.0048375256,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00023397120000000018,
"min": 0.00023397120000000018,
"max": 0.012371866799999999,
"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": "1775118763",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1775119160"
},
"total": 397.05866776034236,
"count": 1,
"self": 0.37466171756386757,
"children": {
"run_training.setup": {
"total": 0.03347459435462952,
"count": 1,
"self": 0.03347459435462952
},
"TrainerController.start_learning": {
"total": 396.65053144842386,
"count": 1,
"self": 0.33265311270952225,
"children": {
"TrainerController._reset_env": {
"total": 3.2625728100538254,
"count": 1,
"self": 3.2625728100538254
},
"TrainerController.advance": {
"total": 392.9706822782755,
"count": 18192,
"self": 0.3458873853087425,
"children": {
"env_step": {
"total": 284.9008002281189,
"count": 18192,
"self": 210.52193197980523,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.16406241059303,
"count": 18192,
"self": 1.1197093203663826,
"children": {
"TorchPolicy.evaluate": {
"total": 73.04435309022665,
"count": 18192,
"self": 73.04435309022665
}
}
},
"workers": {
"total": 0.21480583772063255,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 395.7958932854235,
"count": 18192,
"is_parallel": true,
"self": 210.94659991934896,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002384953200817108,
"count": 1,
"is_parallel": true,
"self": 0.0006044395267963409,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017805136740207672,
"count": 10,
"is_parallel": true,
"self": 0.0017805136740207672
}
}
},
"UnityEnvironment.step": {
"total": 0.026256851851940155,
"count": 1,
"is_parallel": true,
"self": 0.00036972761154174805,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00031153857707977295,
"count": 1,
"is_parallel": true,
"self": 0.00031153857707977295
},
"communicator.exchange": {
"total": 0.024255141615867615,
"count": 1,
"is_parallel": true,
"self": 0.024255141615867615
},
"steps_from_proto": {
"total": 0.0013204440474510193,
"count": 1,
"is_parallel": true,
"self": 0.000277835875749588,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010426081717014313,
"count": 10,
"is_parallel": true,
"self": 0.0010426081717014313
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 184.84929336607456,
"count": 18191,
"is_parallel": true,
"self": 6.107296582311392,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.869027551263571,
"count": 18191,
"is_parallel": true,
"self": 3.869027551263571
},
"communicator.exchange": {
"total": 151.95482360944152,
"count": 18191,
"is_parallel": true,
"self": 151.95482360944152
},
"steps_from_proto": {
"total": 22.91814562305808,
"count": 18191,
"is_parallel": true,
"self": 4.461108352988958,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.457037270069122,
"count": 181910,
"is_parallel": true,
"self": 18.457037270069122
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 107.72399466484785,
"count": 18192,
"self": 0.3453129008412361,
"children": {
"process_trajectory": {
"total": 31.468511808663607,
"count": 18192,
"self": 31.07860343530774,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3899083733558655,
"count": 4,
"self": 0.3899083733558655
}
}
},
"_update_policy": {
"total": 75.91016995534301,
"count": 45,
"self": 57.96003883332014,
"children": {
"TorchPPOOptimizer.update": {
"total": 17.950131122022867,
"count": 1080,
"self": 17.950131122022867
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.94652509689331e-07,
"count": 1,
"self": 9.94652509689331e-07
},
"TrainerController._save_models": {
"total": 0.08462225273251534,
"count": 1,
"self": 0.0007707029581069946,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08385154977440834,
"count": 1,
"self": 0.08385154977440834
}
}
}
}
}
}
}