duongkstn's picture
first commit
73492a9
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9552689790725708,
"min": 0.9539012908935547,
"max": 2.8512349128723145,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9120.908203125,
"min": 9120.908203125,
"max": 29199.49609375,
"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": 13.474652290344238,
"min": 0.4769231677055359,
"max": 13.474652290344238,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2627.55712890625,
"min": 92.5230941772461,
"max": 2734.80859375,
"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": 0.06914733744997648,
"min": 0.064778363431512,
"max": 0.07241822536825031,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2765893497999059,
"min": 0.259113453726048,
"max": 0.3536902416353983,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19181358972016502,
"min": 0.13847277060027838,
"max": 0.26779350301798654,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7672543588806601,
"min": 0.5538910824011135,
"max": 1.3389675150899327,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.0013851600382799997,
"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": 0.9617200000000001,
"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": 26.363636363636363,
"min": 3.8863636363636362,
"max": 26.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1160.0,
"min": 171.0,
"max": 1448.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.363636363636363,
"min": 3.8863636363636362,
"max": 26.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1160.0,
"min": 171.0,
"max": 1448.0,
"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": "1673855199",
"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 --force",
"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": "1673855818"
},
"total": 618.5219788109998,
"count": 1,
"self": 0.3855124059996342,
"children": {
"run_training.setup": {
"total": 0.11510795200001667,
"count": 1,
"self": 0.11510795200001667
},
"TrainerController.start_learning": {
"total": 618.0213584530002,
"count": 1,
"self": 0.5348692059656059,
"children": {
"TrainerController._reset_env": {
"total": 6.329385505000118,
"count": 1,
"self": 6.329385505000118
},
"TrainerController.advance": {
"total": 611.0238416710345,
"count": 18202,
"self": 0.27823286102147904,
"children": {
"env_step": {
"total": 610.745608810013,
"count": 18202,
"self": 465.4346205270608,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.02605725098056,
"count": 18202,
"self": 1.3547999501183767,
"children": {
"TorchPolicy.evaluate": {
"total": 143.67125730086218,
"count": 18202,
"self": 32.52508133388528,
"children": {
"TorchPolicy.sample_actions": {
"total": 111.1461759669769,
"count": 18202,
"self": 111.1461759669769
}
}
}
}
},
"workers": {
"total": 0.2849310319716096,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 616.7889282609867,
"count": 18202,
"is_parallel": true,
"self": 395.74840690700375,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0026085720000992296,
"count": 1,
"is_parallel": true,
"self": 0.0007648099995094526,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001843762000589777,
"count": 10,
"is_parallel": true,
"self": 0.001843762000589777
}
}
},
"UnityEnvironment.step": {
"total": 0.0321357379998517,
"count": 1,
"is_parallel": true,
"self": 0.0004936440000165021,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002719869999054936,
"count": 1,
"is_parallel": true,
"self": 0.0002719869999054936
},
"communicator.exchange": {
"total": 0.029581526999663765,
"count": 1,
"is_parallel": true,
"self": 0.029581526999663765
},
"steps_from_proto": {
"total": 0.001788580000265938,
"count": 1,
"is_parallel": true,
"self": 0.00040616200067233876,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013824179995935992,
"count": 10,
"is_parallel": true,
"self": 0.0013824179995935992
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 221.04052135398297,
"count": 18201,
"is_parallel": true,
"self": 8.292956076988503,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.856066705030571,
"count": 18201,
"is_parallel": true,
"self": 4.856066705030571
},
"communicator.exchange": {
"total": 177.9031288909796,
"count": 18201,
"is_parallel": true,
"self": 177.9031288909796
},
"steps_from_proto": {
"total": 29.988369680984306,
"count": 18201,
"is_parallel": true,
"self": 6.518819605980752,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.469550075003554,
"count": 182010,
"is_parallel": true,
"self": 23.469550075003554
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.5419999878504314e-05,
"count": 1,
"self": 4.5419999878504314e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 608.2015263780877,
"count": 340688,
"is_parallel": true,
"self": 8.704316748092424,
"children": {
"process_trajectory": {
"total": 240.56946291799522,
"count": 340688,
"is_parallel": true,
"self": 239.7757508689965,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7937120489987137,
"count": 4,
"is_parallel": true,
"self": 0.7937120489987137
}
}
},
"_update_policy": {
"total": 358.92774671200004,
"count": 90,
"is_parallel": true,
"self": 137.6421361100147,
"children": {
"TorchPPOOptimizer.update": {
"total": 221.28561060198535,
"count": 15290,
"is_parallel": true,
"self": 221.28561060198535
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1332166510001116,
"count": 1,
"self": 0.0012538530008896487,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13196279799922195,
"count": 1,
"self": 0.13196279799922195
}
}
}
}
}
}
}