ppo-Huggy / run_logs /timers.json
SatCat's picture
Huggy
70fa47a
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4123016595840454,
"min": 1.4123016595840454,
"max": 1.4335674047470093,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71600.8671875,
"min": 69225.3203125,
"max": 75309.9375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 78.82456140350877,
"min": 74.02980625931446,
"max": 370.8888888888889,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49423.0,
"min": 48997.0,
"max": 50070.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999913.0,
"min": 49793.0,
"max": 1999913.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999913.0,
"min": 49793.0,
"max": 1999913.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4988551139831543,
"min": 0.11209988594055176,
"max": 2.4988551139831543,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1566.7821044921875,
"min": 15.021384239196777,
"max": 1605.2821044921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9312498891752874,
"min": 1.7945782413233573,
"max": 4.038494653607669,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2464.893680512905,
"min": 240.47348433732986,
"max": 2557.696433067322,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9312498891752874,
"min": 1.7945782413233573,
"max": 4.038494653607669,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2464.893680512905,
"min": 240.47348433732986,
"max": 2557.696433067322,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01899629915585845,
"min": 0.013273557735374197,
"max": 0.020059046493649174,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05698889746757535,
"min": 0.026547115470748395,
"max": 0.05740660231676884,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05727169737219811,
"min": 0.0224095675162971,
"max": 0.05867371348043283,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17181509211659432,
"min": 0.0448191350325942,
"max": 0.17181509211659432,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.872348709250011e-06,
"min": 3.872348709250011e-06,
"max": 0.0002952854265715249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1617046127750032e-05,
"min": 1.1617046127750032e-05,
"max": 0.0008441916186028,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10129075000000003,
"min": 0.10129075000000003,
"max": 0.19842847500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30387225000000007,
"min": 0.2077581,
"max": 0.5813972000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.440842500000017e-05,
"min": 7.440842500000017e-05,
"max": 0.0049215809025,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002232252750000005,
"min": 0.0002232252750000005,
"max": 0.014071720280000005,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1670545747",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1.21.6",
"end_time_seconds": "1670548016"
},
"total": 2268.5020343280003,
"count": 1,
"self": 0.3896853280002688,
"children": {
"run_training.setup": {
"total": 0.10975254799996037,
"count": 1,
"self": 0.10975254799996037
},
"TrainerController.start_learning": {
"total": 2268.002596452,
"count": 1,
"self": 3.9191365989386213,
"children": {
"TrainerController._reset_env": {
"total": 11.087398874999963,
"count": 1,
"self": 11.087398874999963
},
"TrainerController.advance": {
"total": 2252.8840705190614,
"count": 233189,
"self": 4.088741679126997,
"children": {
"env_step": {
"total": 1765.8541187240057,
"count": 233189,
"self": 1482.6262444138504,
"children": {
"SubprocessEnvManager._take_step": {
"total": 280.63031157018645,
"count": 233189,
"self": 14.436969990224043,
"children": {
"TorchPolicy.evaluate": {
"total": 266.1933415799624,
"count": 222927,
"self": 67.10545327602699,
"children": {
"TorchPolicy.sample_actions": {
"total": 199.08788830393542,
"count": 222927,
"self": 199.08788830393542
}
}
}
}
},
"workers": {
"total": 2.5975627399689074,
"count": 233189,
"self": 0.0,
"children": {
"worker_root": {
"total": 2260.158810420019,
"count": 233189,
"is_parallel": true,
"self": 1037.6240056931558,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023008890000255633,
"count": 1,
"is_parallel": true,
"self": 0.00034413300022606563,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019567559997994977,
"count": 2,
"is_parallel": true,
"self": 0.0019567559997994977
}
}
},
"UnityEnvironment.step": {
"total": 0.027403158999959487,
"count": 1,
"is_parallel": true,
"self": 0.00029102999997121515,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020465200009311957,
"count": 1,
"is_parallel": true,
"self": 0.00020465200009311957
},
"communicator.exchange": {
"total": 0.026141317999872626,
"count": 1,
"is_parallel": true,
"self": 0.026141317999872626
},
"steps_from_proto": {
"total": 0.000766159000022526,
"count": 1,
"is_parallel": true,
"self": 0.0002601860001050227,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005059729999175033,
"count": 2,
"is_parallel": true,
"self": 0.0005059729999175033
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1222.5348047268633,
"count": 233188,
"is_parallel": true,
"self": 35.057547287862235,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.95110975598095,
"count": 233188,
"is_parallel": true,
"self": 76.95110975598095
},
"communicator.exchange": {
"total": 1016.3740179680469,
"count": 233188,
"is_parallel": true,
"self": 1016.3740179680469
},
"steps_from_proto": {
"total": 94.15212971497317,
"count": 233188,
"is_parallel": true,
"self": 39.086173823863646,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.065955891109525,
"count": 466376,
"is_parallel": true,
"self": 55.065955891109525
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 482.9412101159287,
"count": 233189,
"self": 6.012637034858017,
"children": {
"process_trajectory": {
"total": 152.67396775407065,
"count": 233189,
"self": 152.20461524407074,
"children": {
"RLTrainer._checkpoint": {
"total": 0.46935250999990785,
"count": 4,
"self": 0.46935250999990785
}
}
},
"_update_policy": {
"total": 324.25460532700004,
"count": 97,
"self": 270.4577324020081,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.79687292499193,
"count": 2910,
"self": 53.79687292499193
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.679999154992402e-07,
"count": 1,
"self": 8.679999154992402e-07
},
"TrainerController._save_models": {
"total": 0.11198959100011052,
"count": 1,
"self": 0.002042630000232748,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10994696099987777,
"count": 1,
"self": 0.10994696099987777
}
}
}
}
}
}
}