mwissing's picture
First Push
41f84ce
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.986212432384491,
"min": 0.9837126731872559,
"max": 2.8696908950805664,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9416.3564453125,
"min": 9416.3564453125,
"max": 29388.50390625,
"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": 13.067465782165527,
"min": 0.42855897545814514,
"max": 13.067465782165527,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2548.15576171875,
"min": 83.14044189453125,
"max": 2656.00146484375,
"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": 0.07289296375015777,
"min": 0.06215525681849006,
"max": 0.07771197744039135,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2915718550006311,
"min": 0.24862102727396024,
"max": 0.3564113635545843,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1793919273962577,
"min": 0.11363111478025459,
"max": 0.27907180077597205,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7175677095850308,
"min": 0.45452445912101835,
"max": 1.379257349991331,
"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": 25.65909090909091,
"min": 3.409090909090909,
"max": 25.854545454545455,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1129.0,
"min": 150.0,
"max": 1422.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.65909090909091,
"min": 3.409090909090909,
"max": 25.854545454545455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1129.0,
"min": 150.0,
"max": 1422.0,
"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": "1677155154",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677155622"
},
"total": 468.12924302799996,
"count": 1,
"self": 0.4359287139999424,
"children": {
"run_training.setup": {
"total": 0.11555200300000479,
"count": 1,
"self": 0.11555200300000479
},
"TrainerController.start_learning": {
"total": 467.577762311,
"count": 1,
"self": 0.555388742002151,
"children": {
"TrainerController._reset_env": {
"total": 9.455609559000038,
"count": 1,
"self": 9.455609559000038
},
"TrainerController.advance": {
"total": 457.4486552739979,
"count": 18202,
"self": 0.28548002498700953,
"children": {
"env_step": {
"total": 457.16317524901086,
"count": 18202,
"self": 314.2625233740217,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.62013486799225,
"count": 18202,
"self": 1.5389652789904176,
"children": {
"TorchPolicy.evaluate": {
"total": 141.08116958900183,
"count": 18202,
"self": 31.945539317009718,
"children": {
"TorchPolicy.sample_actions": {
"total": 109.13563027199211,
"count": 18202,
"self": 109.13563027199211
}
}
}
}
},
"workers": {
"total": 0.2805170069968881,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 466.07960778700595,
"count": 18202,
"is_parallel": true,
"self": 226.87201776400553,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0060553220000088,
"count": 1,
"is_parallel": true,
"self": 0.004215336000015668,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018399859999931323,
"count": 10,
"is_parallel": true,
"self": 0.0018399859999931323
}
}
},
"UnityEnvironment.step": {
"total": 0.046346752000033575,
"count": 1,
"is_parallel": true,
"self": 0.0005960320000326647,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003689119999989998,
"count": 1,
"is_parallel": true,
"self": 0.0003689119999989998
},
"communicator.exchange": {
"total": 0.043574575999969056,
"count": 1,
"is_parallel": true,
"self": 0.043574575999969056
},
"steps_from_proto": {
"total": 0.0018072320000328546,
"count": 1,
"is_parallel": true,
"self": 0.00041088500000796557,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001396347000024889,
"count": 10,
"is_parallel": true,
"self": 0.001396347000024889
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.20759002300042,
"count": 18201,
"is_parallel": true,
"self": 9.61591975900285,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.218097030994386,
"count": 18201,
"is_parallel": true,
"self": 5.218097030994386
},
"communicator.exchange": {
"total": 192.61370886200496,
"count": 18201,
"is_parallel": true,
"self": 192.61370886200496
},
"steps_from_proto": {
"total": 31.75986437099823,
"count": 18201,
"is_parallel": true,
"self": 7.004827706993581,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.75503666400465,
"count": 182010,
"is_parallel": true,
"self": 24.75503666400465
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015012099993327865,
"count": 1,
"self": 0.00015012099993327865,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 454.14583430605876,
"count": 398712,
"is_parallel": true,
"self": 10.065984651065833,
"children": {
"process_trajectory": {
"total": 258.1655246549924,
"count": 398712,
"is_parallel": true,
"self": 256.9687998859923,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1967247690000704,
"count": 4,
"is_parallel": true,
"self": 1.1967247690000704
}
}
},
"_update_policy": {
"total": 185.91432500000053,
"count": 90,
"is_parallel": true,
"self": 63.48815723600012,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.42616776400041,
"count": 4584,
"is_parallel": true,
"self": 122.42616776400041
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11795861500002047,
"count": 1,
"self": 0.0008879040000238092,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11707071099999666,
"count": 1,
"self": 0.11707071099999666
}
}
}
}
}
}
}