ppo-PyramidsRND / run_logs /timers.json
Emperor-WS's picture
First Push
2dafab7
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.609352469444275,
"min": 1.6093497276306152,
"max": 1.6093556880950928,
"count": 10
},
"Pyramids.Policy.Entropy.sum": {
"value": 48203.32421875,
"min": 48203.2421875,
"max": 48821.4140625,
"count": 10
},
"Pyramids.Step.mean": {
"value": 299904.0,
"min": 29952.0,
"max": 299904.0,
"count": 10
},
"Pyramids.Step.sum": {
"value": 299904.0,
"min": 29952.0,
"max": 299904.0,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.000882952765095979,
"min": -0.0023768970277160406,
"max": 0.004060596693307161,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.21190866827964783,
"min": -0.5728321671485901,
"max": 0.9623613953590393,
"count": 10
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.08448433876037598,
"min": 0.08175806701183319,
"max": 0.08648084104061127,
"count": 10
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 20.276241302490234,
"min": 19.458419799804688,
"max": 20.755401611328125,
"count": 10
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 999.0,
"max": 999.0,
"count": 10
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31968.0,
"min": 15984.0,
"max": 31968.0,
"count": 10
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -1.0000000521540642,
"count": 10
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -32.000001668930054,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 10
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -1.0000000521540642,
"count": 10
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -32.000001668930054,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 10
},
"Pyramids.Policy.RndReward.mean": {
"value": 24.956031378358603,
"min": 24.675856741035687,
"max": 27.15653832256794,
"count": 10
},
"Pyramids.Policy.RndReward.sum": {
"value": 798.5930041074753,
"min": 419.118003487587,
"max": 869.0092263221741,
"count": 10
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1690403150",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
"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": "1690403564"
},
"total": 414.56048932800013,
"count": 1,
"self": 0.48192445300037434,
"children": {
"run_training.setup": {
"total": 0.031045514999732404,
"count": 1,
"self": 0.031045514999732404
},
"TrainerController.start_learning": {
"total": 414.04751936,
"count": 1,
"self": 0.5032779090115582,
"children": {
"TrainerController._reset_env": {
"total": 4.0870087729999796,
"count": 1,
"self": 4.0870087729999796
},
"TrainerController.advance": {
"total": 409.36576379698863,
"count": 18768,
"self": 0.4896660119720764,
"children": {
"env_step": {
"total": 372.4287868499887,
"count": 18768,
"self": 331.5242142190082,
"children": {
"SubprocessEnvManager._take_step": {
"total": 40.61062958494722,
"count": 18768,
"self": 1.6262726340137306,
"children": {
"TorchPolicy.evaluate": {
"total": 38.98435695093349,
"count": 18768,
"self": 38.98435695093349
}
}
},
"workers": {
"total": 0.29394304603329147,
"count": 18768,
"self": 0.0,
"children": {
"worker_root": {
"total": 412.2022637330215,
"count": 18768,
"is_parallel": true,
"self": 119.68806192904458,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019146859999636945,
"count": 1,
"is_parallel": true,
"self": 0.0006268099996304954,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001287876000333199,
"count": 8,
"is_parallel": true,
"self": 0.001287876000333199
}
}
},
"UnityEnvironment.step": {
"total": 0.050881787999969674,
"count": 1,
"is_parallel": true,
"self": 0.0006964270000935358,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005387689998315182,
"count": 1,
"is_parallel": true,
"self": 0.0005387689998315182
},
"communicator.exchange": {
"total": 0.04767622100007429,
"count": 1,
"is_parallel": true,
"self": 0.04767622100007429
},
"steps_from_proto": {
"total": 0.001970370999970328,
"count": 1,
"is_parallel": true,
"self": 0.00040276599929711665,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015676050006732112,
"count": 8,
"is_parallel": true,
"self": 0.0015676050006732112
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 292.5142018039769,
"count": 18767,
"is_parallel": true,
"self": 10.795628282918187,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.537779233026413,
"count": 18767,
"is_parallel": true,
"self": 7.537779233026413
},
"communicator.exchange": {
"total": 241.44279749303496,
"count": 18767,
"is_parallel": true,
"self": 241.44279749303496
},
"steps_from_proto": {
"total": 32.73799679499734,
"count": 18767,
"is_parallel": true,
"self": 6.755121638010678,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.982875156986665,
"count": 150136,
"is_parallel": true,
"self": 25.982875156986665
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 36.44731093502787,
"count": 18768,
"self": 0.5383073790108028,
"children": {
"process_trajectory": {
"total": 35.90900355601707,
"count": 18768,
"self": 35.90900355601707
}
}
}
}
},
"trainer_threads": {
"total": 1.0039998414868023e-06,
"count": 1,
"self": 1.0039998414868023e-06
},
"TrainerController._save_models": {
"total": 0.09146787700001369,
"count": 1,
"self": 0.0007240079999064619,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09074386900010722,
"count": 1,
"self": 0.09074386900010722
}
}
}
}
}
}
}