xenjin450's picture
First Push
3686dfb verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6928920745849609,
"min": 0.6928920745849609,
"max": 2.878577470779419,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6646.220703125,
"min": 6646.220703125,
"max": 29574.50390625,
"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": 11.981770515441895,
"min": 0.29059553146362305,
"max": 11.981770515441895,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2336.4453125,
"min": 56.37553405761719,
"max": 2440.07568359375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0296454241455649,
"min": 0.028084085073787724,
"max": 0.037452506452100354,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.1185816965822596,
"min": 0.1185816965822596,
"max": 0.18726253226050177,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19328838884830474,
"min": 0.10373825123533606,
"max": 0.290578506141901,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.773153555393219,
"min": 0.41495300494134424,
"max": 1.3859055444598198,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.077609730600001e-05,
"min": 1.077609730600001e-05,
"max": 0.000389176002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.310438922400004e-05,
"min": 4.310438922400004e-05,
"max": 0.0018468800382800002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105388,
"min": 0.105388,
"max": 0.294588,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.421552,
"min": 0.421552,
"max": 1.42344,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014443060000000015,
"min": 0.00014443060000000015,
"max": 0.004864970600000001,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000006,
"min": 0.0005777224000000006,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 23.681818181818183,
"min": 2.6818181818181817,
"max": 23.70909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1042.0,
"min": 118.0,
"max": 1304.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.681818181818183,
"min": 2.6818181818181817,
"max": 23.70909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1042.0,
"min": 118.0,
"max": 1304.0,
"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": "1738662694",
"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=SnowballTargetXenjin450 --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": "1738663506"
},
"total": 812.5668383210004,
"count": 1,
"self": 0.6927915620008207,
"children": {
"run_training.setup": {
"total": 0.03452016699975502,
"count": 1,
"self": 0.03452016699975502
},
"TrainerController.start_learning": {
"total": 811.8395265919999,
"count": 1,
"self": 1.07995954297985,
"children": {
"TrainerController._reset_env": {
"total": 3.42389432499931,
"count": 1,
"self": 3.42389432499931
},
"TrainerController.advance": {
"total": 807.1814257440201,
"count": 18206,
"self": 0.49803600401173753,
"children": {
"env_step": {
"total": 806.6833897400084,
"count": 18206,
"self": 640.9386373739844,
"children": {
"SubprocessEnvManager._take_step": {
"total": 165.25657096709983,
"count": 18206,
"self": 2.93720667904563,
"children": {
"TorchPolicy.evaluate": {
"total": 162.3193642880542,
"count": 18206,
"self": 162.3193642880542
}
}
},
"workers": {
"total": 0.4881813989240982,
"count": 18206,
"self": 0.0,
"children": {
"worker_root": {
"total": 809.5793749020659,
"count": 18206,
"is_parallel": true,
"self": 463.8940645060702,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004620794999937061,
"count": 1,
"is_parallel": true,
"self": 0.001583236999977089,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0030375579999599722,
"count": 10,
"is_parallel": true,
"self": 0.0030375579999599722
}
}
},
"UnityEnvironment.step": {
"total": 0.15677927999968233,
"count": 1,
"is_parallel": true,
"self": 0.0037805080000907765,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004818150000573951,
"count": 1,
"is_parallel": true,
"self": 0.0004818150000573951
},
"communicator.exchange": {
"total": 0.13114621299973805,
"count": 1,
"is_parallel": true,
"self": 0.13114621299973805
},
"steps_from_proto": {
"total": 0.021370743999796105,
"count": 1,
"is_parallel": true,
"self": 0.005355924999093986,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.01601481900070212,
"count": 10,
"is_parallel": true,
"self": 0.01601481900070212
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 345.68531039599566,
"count": 18205,
"is_parallel": true,
"self": 14.406276040003831,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.994227226001385,
"count": 18205,
"is_parallel": true,
"self": 7.994227226001385
},
"communicator.exchange": {
"total": 278.1204304049734,
"count": 18205,
"is_parallel": true,
"self": 278.1204304049734
},
"steps_from_proto": {
"total": 45.164376725017064,
"count": 18205,
"is_parallel": true,
"self": 9.234507885953462,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.9298688390636,
"count": 182050,
"is_parallel": true,
"self": 35.9298688390636
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00023182800032373052,
"count": 1,
"self": 0.00023182800032373052,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 800.2991470469851,
"count": 828679,
"is_parallel": true,
"self": 18.937228551389126,
"children": {
"process_trajectory": {
"total": 362.3103792215943,
"count": 828679,
"is_parallel": true,
"self": 360.76179730759395,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5485819140003514,
"count": 4,
"is_parallel": true,
"self": 1.5485819140003514
}
}
},
"_update_policy": {
"total": 419.0515392740017,
"count": 90,
"is_parallel": true,
"self": 98.93746979500156,
"children": {
"TorchPPOOptimizer.update": {
"total": 320.11406947900014,
"count": 1800,
"is_parallel": true,
"self": 320.11406947900014
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1540151520002837,
"count": 1,
"self": 0.004700188000242633,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14931496400004107,
"count": 1,
"self": 0.14931496400004107
}
}
}
}
}
}
}