Unterwexi's picture
First commit with 200k steps training
3ebdc90
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9185094237327576,
"min": 0.9170023798942566,
"max": 2.8593344688415527,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8759.82421875,
"min": 8759.82421875,
"max": 29282.443359375,
"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": 12.83442211151123,
"min": 0.3415834903717041,
"max": 12.83442211151123,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2502.71240234375,
"min": 66.26719665527344,
"max": 2579.66650390625,
"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": 0.06926004364882543,
"min": 0.0633829925246377,
"max": 0.07793401975707406,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2770401745953017,
"min": 0.2535319700985508,
"max": 0.38967009878537034,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20761140556458166,
"min": 0.11949993273147436,
"max": 0.2817226437230905,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8304456222583266,
"min": 0.4779997309258974,
"max": 1.3316025748556735,
"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": 25.454545454545453,
"min": 3.4318181818181817,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1120.0,
"min": 151.0,
"max": 1394.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.454545454545453,
"min": 3.4318181818181817,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1120.0,
"min": 151.0,
"max": 1394.0,
"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": "1673506760",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673507203"
},
"total": 442.975137849,
"count": 1,
"self": 0.3899906020000117,
"children": {
"run_training.setup": {
"total": 0.11524706199998036,
"count": 1,
"self": 0.11524706199998036
},
"TrainerController.start_learning": {
"total": 442.46990018500003,
"count": 1,
"self": 0.5442870550120915,
"children": {
"TrainerController._reset_env": {
"total": 6.875254969000025,
"count": 1,
"self": 6.875254969000025
},
"TrainerController.advance": {
"total": 434.9241928489879,
"count": 18200,
"self": 0.29331878299365144,
"children": {
"env_step": {
"total": 434.63087406599425,
"count": 18200,
"self": 284.94134216198256,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.3834507500112,
"count": 18200,
"self": 1.4663358860151448,
"children": {
"TorchPolicy.evaluate": {
"total": 147.91711486399606,
"count": 18200,
"self": 33.16146721099449,
"children": {
"TorchPolicy.sample_actions": {
"total": 114.75564765300157,
"count": 18200,
"self": 114.75564765300157
}
}
}
}
},
"workers": {
"total": 0.30608115400048064,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 441.1719897929952,
"count": 18200,
"is_parallel": true,
"self": 212.46321033200445,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0061073890000216124,
"count": 1,
"is_parallel": true,
"self": 0.0037500120000686366,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002357376999952976,
"count": 10,
"is_parallel": true,
"self": 0.002357376999952976
}
}
},
"UnityEnvironment.step": {
"total": 0.0424696469999617,
"count": 1,
"is_parallel": true,
"self": 0.0004353610000862318,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003050389999543768,
"count": 1,
"is_parallel": true,
"self": 0.0003050389999543768
},
"communicator.exchange": {
"total": 0.04023807399994439,
"count": 1,
"is_parallel": true,
"self": 0.04023807399994439
},
"steps_from_proto": {
"total": 0.0014911729999766976,
"count": 1,
"is_parallel": true,
"self": 0.000378893000060998,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011122799999156996,
"count": 10,
"is_parallel": true,
"self": 0.0011122799999156996
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 228.70877946099074,
"count": 18199,
"is_parallel": true,
"self": 8.636070926978391,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.244195679999507,
"count": 18199,
"is_parallel": true,
"self": 5.244195679999507
},
"communicator.exchange": {
"total": 182.98735432301305,
"count": 18199,
"is_parallel": true,
"self": 182.98735432301305
},
"steps_from_proto": {
"total": 31.84115853099979,
"count": 18199,
"is_parallel": true,
"self": 7.082800903990233,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.75835762700956,
"count": 181990,
"is_parallel": true,
"self": 24.75835762700956
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.916299997148599e-05,
"count": 1,
"self": 4.916299997148599e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 431.8073671630193,
"count": 347284,
"is_parallel": true,
"self": 9.352737155012619,
"children": {
"process_trajectory": {
"total": 247.32695583200666,
"count": 347284,
"is_parallel": true,
"self": 246.50195027300663,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8250055590000329,
"count": 4,
"is_parallel": true,
"self": 0.8250055590000329
}
}
},
"_update_policy": {
"total": 175.12767417600003,
"count": 90,
"is_parallel": true,
"self": 44.778259038002375,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.34941513799765,
"count": 4587,
"is_parallel": true,
"self": 130.34941513799765
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12611614900004042,
"count": 1,
"self": 0.0008863730000712167,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1252297759999692,
"count": 1,
"self": 0.1252297759999692
}
}
}
}
}
}
}