dineshresearch's picture
First Push
e31a6a6
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.739715576171875,
"min": 1.739715576171875,
"max": 2.862865924835205,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 17892.974609375,
"min": 17423.359375,
"max": 29350.1015625,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 8.553292274475098,
"min": 0.3625592589378357,
"max": 8.553292274475098,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1744.87158203125,
"min": 70.33649444580078,
"max": 1744.87158203125,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06695646024805577,
"min": 0.05916602577881171,
"max": 0.07083965575250606,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3347823012402788,
"min": 0.23666410311524683,
"max": 0.34921885291409765,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.28118227866350437,
"min": 0.1225745251171711,
"max": 0.29989151444797424,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.4059113933175218,
"min": 0.4902981004686844,
"max": 1.4059113933175218,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.6464094511999996e-05,
"min": 1.6464094511999996e-05,
"max": 0.000283764005412,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.232047255999999e-05,
"min": 8.232047255999999e-05,
"max": 0.00127032007656,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105488,
"min": 0.105488,
"max": 0.194588,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.52744,
"min": 0.4615520000000001,
"max": 0.92344,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002838512,
"min": 0.0002838512,
"max": 0.0047299412,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.001419256,
"min": 0.001419256,
"max": 0.021179656,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 17.836363636363636,
"min": 3.5681818181818183,
"max": 17.836363636363636,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 981.0,
"min": 157.0,
"max": 981.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 17.836363636363636,
"min": 3.5681818181818183,
"max": 17.836363636363636,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 981.0,
"min": 157.0,
"max": 981.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1678383741",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1678383982"
},
"total": 240.41169207199994,
"count": 1,
"self": 0.3861476989999346,
"children": {
"run_training.setup": {
"total": 0.1259657169999855,
"count": 1,
"self": 0.1259657169999855
},
"TrainerController.start_learning": {
"total": 239.89957865600002,
"count": 1,
"self": 0.28994595200333606,
"children": {
"TrainerController._reset_env": {
"total": 10.46877641900005,
"count": 1,
"self": 10.46877641900005
},
"TrainerController.advance": {
"total": 228.99166047599658,
"count": 9132,
"self": 0.13197067899864123,
"children": {
"env_step": {
"total": 228.85968979699794,
"count": 9132,
"self": 164.5536440720001,
"children": {
"SubprocessEnvManager._take_step": {
"total": 64.17153410900426,
"count": 9132,
"self": 1.154353386001162,
"children": {
"TorchPolicy.evaluate": {
"total": 63.017180723003094,
"count": 9132,
"self": 63.017180723003094
}
}
},
"workers": {
"total": 0.1345116159935742,
"count": 9132,
"self": 0.0,
"children": {
"worker_root": {
"total": 239.140122159999,
"count": 9132,
"is_parallel": true,
"self": 117.1265914789966,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006004837999967094,
"count": 1,
"is_parallel": true,
"self": 0.004557657000191284,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00144718099977581,
"count": 10,
"is_parallel": true,
"self": 0.00144718099977581
}
}
},
"UnityEnvironment.step": {
"total": 0.04391339100004643,
"count": 1,
"is_parallel": true,
"self": 0.0006100230000356532,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024881400008780474,
"count": 1,
"is_parallel": true,
"self": 0.00024881400008780474
},
"communicator.exchange": {
"total": 0.041243864999955804,
"count": 1,
"is_parallel": true,
"self": 0.041243864999955804
},
"steps_from_proto": {
"total": 0.0018106889999671694,
"count": 1,
"is_parallel": true,
"self": 0.0003831899998658628,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014274990001013066,
"count": 10,
"is_parallel": true,
"self": 0.0014274990001013066
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 122.01353068100241,
"count": 9131,
"is_parallel": true,
"self": 4.775132064003401,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.6179126060033013,
"count": 9131,
"is_parallel": true,
"self": 2.6179126060033013
},
"communicator.exchange": {
"total": 98.82520414799524,
"count": 9131,
"is_parallel": true,
"self": 98.82520414799524
},
"steps_from_proto": {
"total": 15.795281863000469,
"count": 9131,
"is_parallel": true,
"self": 3.1359750460233045,
"children": {
"_process_rank_one_or_two_observation": {
"total": 12.659306816977164,
"count": 91310,
"is_parallel": true,
"self": 12.659306816977164
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00030548400002317067,
"count": 1,
"self": 0.00030548400002317067,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 227.1595609020053,
"count": 215000,
"is_parallel": true,
"self": 5.342716038007325,
"children": {
"process_trajectory": {
"total": 127.78804120399798,
"count": 215000,
"is_parallel": true,
"self": 127.78804120399798
},
"_update_policy": {
"total": 94.02880366,
"count": 45,
"is_parallel": true,
"self": 32.410513985998364,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.61828967400163,
"count": 2289,
"is_parallel": true,
"self": 61.61828967400163
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14889032500002486,
"count": 1,
"self": 0.0009498620000840674,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1479404629999408,
"count": 1,
"self": 0.1479404629999408
}
}
}
}
}
}
}