soonawg's picture
First Push
7b9a99c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8660266995429993,
"min": 0.8660266995429993,
"max": 2.8600142002105713,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8230.7177734375,
"min": 8230.7177734375,
"max": 29195.025390625,
"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": 12.911713600158691,
"min": 0.41079822182655334,
"max": 12.911713600158691,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2517.7841796875,
"min": 79.69485473632812,
"max": 2626.24609375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06839230692069168,
"min": 0.059458287941447,
"max": 0.07409773503005615,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2735692276827667,
"min": 0.237833151765788,
"max": 0.3704886751502807,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19632433763906068,
"min": 0.12023652598944345,
"max": 0.29982960592297947,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7852973505562427,
"min": 0.4809461039577738,
"max": 1.4991480296148973,
"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.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": 25.65909090909091,
"min": 3.3636363636363638,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1129.0,
"min": 148.0,
"max": 1398.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.65909090909091,
"min": 3.3636363636363638,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1129.0,
"min": 148.0,
"max": 1398.0,
"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": "1742625988",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1742626399"
},
"total": 411.36578446,
"count": 1,
"self": 0.4368280209999966,
"children": {
"run_training.setup": {
"total": 0.023163017999991098,
"count": 1,
"self": 0.023163017999991098
},
"TrainerController.start_learning": {
"total": 410.905793421,
"count": 1,
"self": 0.31020692699905794,
"children": {
"TrainerController._reset_env": {
"total": 3.0570038889999864,
"count": 1,
"self": 3.0570038889999864
},
"TrainerController.advance": {
"total": 407.451112179001,
"count": 18192,
"self": 0.3503836939950702,
"children": {
"env_step": {
"total": 286.40739407399906,
"count": 18192,
"self": 216.480773270998,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.73861280599635,
"count": 18192,
"self": 1.2011159059768488,
"children": {
"TorchPolicy.evaluate": {
"total": 68.5374969000195,
"count": 18192,
"self": 68.5374969000195
}
}
},
"workers": {
"total": 0.1880079970047177,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 409.54700706899786,
"count": 18192,
"is_parallel": true,
"self": 219.61663107000055,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005821255999990171,
"count": 1,
"is_parallel": true,
"self": 0.004315226000016992,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015060299999731797,
"count": 10,
"is_parallel": true,
"self": 0.0015060299999731797
}
}
},
"UnityEnvironment.step": {
"total": 0.06118379999998069,
"count": 1,
"is_parallel": true,
"self": 0.0005897439999671406,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037798800002519783,
"count": 1,
"is_parallel": true,
"self": 0.00037798800002519783
},
"communicator.exchange": {
"total": 0.058436051000001044,
"count": 1,
"is_parallel": true,
"self": 0.058436051000001044
},
"steps_from_proto": {
"total": 0.0017800169999873106,
"count": 1,
"is_parallel": true,
"self": 0.00036300700003266684,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014170099999546437,
"count": 10,
"is_parallel": true,
"self": 0.0014170099999546437
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 189.9303759989973,
"count": 18191,
"is_parallel": true,
"self": 9.430869050995057,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.183960191989968,
"count": 18191,
"is_parallel": true,
"self": 5.183960191989968
},
"communicator.exchange": {
"total": 145.3235977720061,
"count": 18191,
"is_parallel": true,
"self": 145.3235977720061
},
"steps_from_proto": {
"total": 29.99194898400617,
"count": 18191,
"is_parallel": true,
"self": 5.227871860990149,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.764077123016023,
"count": 181910,
"is_parallel": true,
"self": 24.764077123016023
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.69333441100684,
"count": 18192,
"self": 0.3960795270019162,
"children": {
"process_trajectory": {
"total": 26.47968581700576,
"count": 18192,
"self": 26.00506159300579,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4746242239999674,
"count": 4,
"self": 0.4746242239999674
}
}
},
"_update_policy": {
"total": 93.81756906699917,
"count": 90,
"self": 36.81456273900238,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.003006327996786,
"count": 4587,
"self": 57.003006327996786
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.719999868844752e-07,
"count": 1,
"self": 8.719999868844752e-07
},
"TrainerController._save_models": {
"total": 0.08746955399999479,
"count": 1,
"self": 0.0009102509999365793,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08655930300005821,
"count": 1,
"self": 0.08655930300005821
}
}
}
}
}
}
}