ErenDoymus's picture
First Push
53cd0d6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.2954778671264648,
"min": 1.2954778671264648,
"max": 2.877952814102173,
"count": 30
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 13338.240234375,
"min": 12566.8662109375,
"max": 29378.142578125,
"count": 30
},
"SnowballTarget.Step.mean": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Step.sum": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.414948463439941,
"min": 0.1366633027791977,
"max": 13.414948463439941,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2736.6494140625,
"min": 26.51268196105957,
"max": 2736.6494140625,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.527272727272727,
"min": 2.840909090909091,
"max": 26.727272727272727,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1459.0,
"min": 125.0,
"max": 1463.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.527272727272727,
"min": 2.840909090909091,
"max": 26.727272727272727,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1459.0,
"min": 125.0,
"max": 1463.0,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.050218212401138294,
"min": 0.04253931511651471,
"max": 0.056264608693120804,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.15065463720341488,
"min": 0.08507863023302942,
"max": 0.16014007063580826,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21182234366150465,
"min": 0.08696074928978786,
"max": 0.31129810411263914,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.635467030984514,
"min": 0.17392149857957573,
"max": 0.9124784524388173,
"count": 30
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.525431570666661e-06,
"min": 3.525431570666661e-06,
"max": 0.00019565866883733337,
"count": 30
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.0576294711999982e-05,
"min": 1.0576294711999982e-05,
"max": 0.0005297760351120001,
"count": 30
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10176266666666667,
"min": 0.10176266666666667,
"max": 0.19782933333333333,
"count": 30
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.305288,
"min": 0.2108586666666667,
"max": 0.5648880000000001,
"count": 30
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00018609039999999976,
"min": 0.00018609039999999976,
"max": 0.009783150400000003,
"count": 30
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005582711999999993,
"min": 0.0005582711999999993,
"max": 0.0264923112,
"count": 30
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1742308552",
"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": "1742309253"
},
"total": 700.933070739,
"count": 1,
"self": 0.4362794359999498,
"children": {
"run_training.setup": {
"total": 0.022851437000099395,
"count": 1,
"self": 0.022851437000099395
},
"TrainerController.start_learning": {
"total": 700.4739398659999,
"count": 1,
"self": 0.5707519940178827,
"children": {
"TrainerController._reset_env": {
"total": 3.0525086659999943,
"count": 1,
"self": 3.0525086659999943
},
"TrainerController.advance": {
"total": 696.7254079879826,
"count": 27328,
"self": 0.6045544870480626,
"children": {
"env_step": {
"total": 477.3892639119563,
"count": 27328,
"self": 352.8666514079173,
"children": {
"SubprocessEnvManager._take_step": {
"total": 124.19671221103408,
"count": 27328,
"self": 1.969559479079635,
"children": {
"TorchPolicy.evaluate": {
"total": 122.22715273195445,
"count": 27328,
"self": 122.22715273195445
}
}
},
"workers": {
"total": 0.3259002930049064,
"count": 27328,
"self": 0.0,
"children": {
"worker_root": {
"total": 698.3401770039741,
"count": 27328,
"is_parallel": true,
"self": 388.6420969249816,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005517917999895872,
"count": 1,
"is_parallel": true,
"self": 0.003905064000718994,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016128539991768776,
"count": 10,
"is_parallel": true,
"self": 0.0016128539991768776
}
}
},
"UnityEnvironment.step": {
"total": 0.034624170000370214,
"count": 1,
"is_parallel": true,
"self": 0.0006041880005795974,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003668069998639112,
"count": 1,
"is_parallel": true,
"self": 0.0003668069998639112
},
"communicator.exchange": {
"total": 0.03166173699992214,
"count": 1,
"is_parallel": true,
"self": 0.03166173699992214
},
"steps_from_proto": {
"total": 0.001991438000004564,
"count": 1,
"is_parallel": true,
"self": 0.0003592530001697014,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016321849998348625,
"count": 10,
"is_parallel": true,
"self": 0.0016321849998348625
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 309.69808007899246,
"count": 27327,
"is_parallel": true,
"self": 14.921438201,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.357895185964026,
"count": 27327,
"is_parallel": true,
"self": 8.357895185964026
},
"communicator.exchange": {
"total": 237.70206348697138,
"count": 27327,
"is_parallel": true,
"self": 237.70206348697138
},
"steps_from_proto": {
"total": 48.71668320505705,
"count": 27327,
"is_parallel": true,
"self": 8.817797180093294,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.89888602496376,
"count": 273270,
"is_parallel": true,
"self": 39.89888602496376
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 218.7315895889783,
"count": 27328,
"self": 0.6764631790101703,
"children": {
"process_trajectory": {
"total": 73.44809073696842,
"count": 27328,
"self": 72.48416731096813,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9639234260002922,
"count": 6,
"self": 0.9639234260002922
}
}
},
"_update_policy": {
"total": 144.6070356729997,
"count": 68,
"self": 77.34293471800493,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.26410095499477,
"count": 4620,
"self": 67.26410095499477
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0129997463081963e-06,
"count": 1,
"self": 1.0129997463081963e-06
},
"TrainerController._save_models": {
"total": 0.12527020499965147,
"count": 1,
"self": 0.00094740499935142,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12432280000030005,
"count": 1,
"self": 0.12432280000030005
}
}
}
}
}
}
}