GEMCorp's picture
First push of training of SnowballTarget
af567e8
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8826402425765991,
"min": 0.8809259533882141,
"max": 2.8680951595306396,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8437.158203125,
"min": 8437.158203125,
"max": 29435.26171875,
"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": 12.847084045410156,
"min": 0.3679988384246826,
"max": 12.878390312194824,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2505.181396484375,
"min": 71.39177703857422,
"max": 2627.191650390625,
"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": 0.0662411142408268,
"min": 0.06224330858950612,
"max": 0.07512338296710011,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2649644569633072,
"min": 0.2489732343580245,
"max": 0.3661886927513086,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19449694111358887,
"min": 0.12949730090650857,
"max": 0.28757514661433653,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7779877644543555,
"min": 0.5179892036260343,
"max": 1.4378757330716827,
"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": 25.0,
"min": 3.6363636363636362,
"max": 25.472727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1100.0,
"min": 160.0,
"max": 1401.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.0,
"min": 3.6363636363636362,
"max": 25.472727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1100.0,
"min": 160.0,
"max": 1401.0,
"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": "1687792059",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1687792690"
},
"total": 630.7080308099999,
"count": 1,
"self": 0.5366265369998473,
"children": {
"run_training.setup": {
"total": 0.050226154000029055,
"count": 1,
"self": 0.050226154000029055
},
"TrainerController.start_learning": {
"total": 630.121178119,
"count": 1,
"self": 0.7895569229822286,
"children": {
"TrainerController._reset_env": {
"total": 5.890731526000309,
"count": 1,
"self": 5.890731526000309
},
"TrainerController.advance": {
"total": 623.2677629480177,
"count": 18202,
"self": 0.4102788760196745,
"children": {
"env_step": {
"total": 622.857484071998,
"count": 18202,
"self": 454.86639834699145,
"children": {
"SubprocessEnvManager._take_step": {
"total": 167.589845771005,
"count": 18202,
"self": 2.415741759039065,
"children": {
"TorchPolicy.evaluate": {
"total": 165.17410401196594,
"count": 18202,
"self": 165.17410401196594
}
}
},
"workers": {
"total": 0.40123995400153945,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 627.9009474450231,
"count": 18202,
"is_parallel": true,
"self": 288.49341277698204,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006249876999845583,
"count": 1,
"is_parallel": true,
"self": 0.004457939999156224,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017919370006893587,
"count": 10,
"is_parallel": true,
"self": 0.0017919370006893587
}
}
},
"UnityEnvironment.step": {
"total": 0.10444021900002554,
"count": 1,
"is_parallel": true,
"self": 0.0006747759998688707,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004894060002698097,
"count": 1,
"is_parallel": true,
"self": 0.0004894060002698097
},
"communicator.exchange": {
"total": 0.10044181900002513,
"count": 1,
"is_parallel": true,
"self": 0.10044181900002513
},
"steps_from_proto": {
"total": 0.002834217999861721,
"count": 1,
"is_parallel": true,
"self": 0.00045187999967311043,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023823380001886107,
"count": 10,
"is_parallel": true,
"self": 0.0023823380001886107
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 339.4075346680411,
"count": 18201,
"is_parallel": true,
"self": 13.675098319978133,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.469836184007363,
"count": 18201,
"is_parallel": true,
"self": 7.469836184007363
},
"communicator.exchange": {
"total": 268.9447039860579,
"count": 18201,
"is_parallel": true,
"self": 268.9447039860579
},
"steps_from_proto": {
"total": 49.31789617799768,
"count": 18201,
"is_parallel": true,
"self": 9.553420299949721,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.76447587804796,
"count": 182010,
"is_parallel": true,
"self": 39.76447587804796
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014111299969954416,
"count": 1,
"self": 0.00014111299969954416,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 617.7001727140519,
"count": 628884,
"is_parallel": true,
"self": 15.093403778165793,
"children": {
"process_trajectory": {
"total": 345.4665238468883,
"count": 628884,
"is_parallel": true,
"self": 344.51590342088775,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9506204260005688,
"count": 4,
"is_parallel": true,
"self": 0.9506204260005688
}
}
},
"_update_policy": {
"total": 257.14024508899774,
"count": 90,
"is_parallel": true,
"self": 97.82155093099709,
"children": {
"TorchPPOOptimizer.update": {
"total": 159.31869415800065,
"count": 4587,
"is_parallel": true,
"self": 159.31869415800065
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.17298560900007942,
"count": 1,
"self": 0.0009772260000318056,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17200838300004762,
"count": 1,
"self": 0.17200838300004762
}
}
}
}
}
}
}