toddwilson147's picture
First Push
ad9b862
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7210003137588501,
"min": 0.7210003137588501,
"max": 2.858285427093506,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6955.48974609375,
"min": 6955.48974609375,
"max": 29366.025390625,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.749482154846191,
"min": 0.47531992197036743,
"max": 13.880439758300781,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2818.643798828125,
"min": 92.21206665039062,
"max": 2831.609619140625,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0709923282188053,
"min": 0.06395676623351927,
"max": 0.07942528764696737,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3549616410940265,
"min": 0.2593081104253132,
"max": 0.370905617689691,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18569634287965062,
"min": 0.13209845879407345,
"max": 0.28231842307483446,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9284817143982531,
"min": 0.5283938351762938,
"max": 1.4115921153741724,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000028e-06,
"min": 3.0528989824000028e-06,
"max": 0.00029675280108239997,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5264494912000015e-05,
"min": 1.5264494912000015e-05,
"max": 0.001454064015312,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000001,
"min": 0.10101760000000001,
"max": 0.19891759999999997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5050880000000001,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0778240000000044e-05,
"min": 6.0778240000000044e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003038912000000002,
"min": 0.0003038912000000002,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.818181818181817,
"min": 3.659090909090909,
"max": 27.155555555555555,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1475.0,
"min": 161.0,
"max": 1486.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.818181818181817,
"min": 3.659090909090909,
"max": 27.155555555555555,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1475.0,
"min": 161.0,
"max": 1486.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1703787159",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703788352"
},
"total": 1193.228377929,
"count": 1,
"self": 0.43248868399996354,
"children": {
"run_training.setup": {
"total": 0.05219223700009934,
"count": 1,
"self": 0.05219223700009934
},
"TrainerController.start_learning": {
"total": 1192.743697008,
"count": 1,
"self": 1.5971916710268488,
"children": {
"TrainerController._reset_env": {
"total": 3.345857660999968,
"count": 1,
"self": 3.345857660999968
},
"TrainerController.advance": {
"total": 1187.6941674139732,
"count": 45474,
"self": 0.8032474519841344,
"children": {
"env_step": {
"total": 1186.890919961989,
"count": 45474,
"self": 782.7650378559986,
"children": {
"SubprocessEnvManager._take_step": {
"total": 403.326378508982,
"count": 45474,
"self": 4.006738198984635,
"children": {
"TorchPolicy.evaluate": {
"total": 399.31964030999734,
"count": 45474,
"self": 399.31964030999734
}
}
},
"workers": {
"total": 0.7995035970085382,
"count": 45474,
"self": 0.0,
"children": {
"worker_root": {
"total": 1189.3697099239996,
"count": 45474,
"is_parallel": true,
"self": 583.9909261340124,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004093484000009084,
"count": 1,
"is_parallel": true,
"self": 0.0025231270000176664,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001570356999991418,
"count": 10,
"is_parallel": true,
"self": 0.001570356999991418
}
}
},
"UnityEnvironment.step": {
"total": 0.08630516200003058,
"count": 1,
"is_parallel": true,
"self": 0.0007188490001226455,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003999309999471734,
"count": 1,
"is_parallel": true,
"self": 0.0003999309999471734
},
"communicator.exchange": {
"total": 0.08283675600000606,
"count": 1,
"is_parallel": true,
"self": 0.08283675600000606
},
"steps_from_proto": {
"total": 0.0023496259999546965,
"count": 1,
"is_parallel": true,
"self": 0.0007513149997748769,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015983110001798195,
"count": 10,
"is_parallel": true,
"self": 0.0015983110001798195
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 605.3787837899872,
"count": 45473,
"is_parallel": true,
"self": 28.556211873972757,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.500349993014993,
"count": 45473,
"is_parallel": true,
"self": 14.500349993014993
},
"communicator.exchange": {
"total": 470.36691087101326,
"count": 45473,
"is_parallel": true,
"self": 470.36691087101326
},
"steps_from_proto": {
"total": 91.9553110519862,
"count": 45473,
"is_parallel": true,
"self": 17.4179898579672,
"children": {
"_process_rank_one_or_two_observation": {
"total": 74.537321194019,
"count": 454730,
"is_parallel": true,
"self": 74.537321194019
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.3316000073900796e-05,
"count": 1,
"self": 4.3316000073900796e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1172.7855061280015,
"count": 1789101,
"is_parallel": true,
"self": 38.62475958805135,
"children": {
"process_trajectory": {
"total": 645.4638755889493,
"count": 1789101,
"is_parallel": true,
"self": 643.6762268149492,
"children": {
"RLTrainer._checkpoint": {
"total": 1.787648774000104,
"count": 10,
"is_parallel": true,
"self": 1.787648774000104
}
}
},
"_update_policy": {
"total": 488.69687095100073,
"count": 227,
"is_parallel": true,
"self": 153.00467796699593,
"children": {
"TorchPPOOptimizer.update": {
"total": 335.6921929840048,
"count": 11574,
"is_parallel": true,
"self": 335.6921929840048
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10643694600003073,
"count": 1,
"self": 0.000998398000092493,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10543854799993824,
"count": 1,
"self": 0.10543854799993824
}
}
}
}
}
}
}