yuval6967's picture
First Push
a7b919f
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3717264235019684,
"min": 0.3636833429336548,
"max": 1.4582184553146362,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11217.216796875,
"min": 10753.388671875,
"max": 44236.515625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989888.0,
"min": 29952.0,
"max": 989888.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989888.0,
"min": 29952.0,
"max": 989888.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5885846614837646,
"min": -0.1287662386894226,
"max": 0.7255609631538391,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 168.335205078125,
"min": -30.517597198486328,
"max": 210.4126739501953,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.010335240513086319,
"min": -0.0637255311012268,
"max": 0.32963666319847107,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.955878734588623,
"min": -17.26961898803711,
"max": 79.44243621826172,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06820477800197079,
"min": 0.06493218341321035,
"max": 0.07459046305733842,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9548668920275911,
"min": 0.5195471508817844,
"max": 1.064879819091099,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016920790609133075,
"min": 0.000963500988674481,
"max": 0.017072917737697084,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23689106852786307,
"min": 0.013489013841442734,
"max": 0.2390208483277592,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.628304600121425e-06,
"min": 7.628304600121425e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010679626440169994,
"min": 0.00010679626440169994,
"max": 0.0036325486891504995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10254273571428572,
"min": 0.10254273571428572,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4355983,
"min": 1.3886848,
"max": 2.6108494999999996,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026401929785714275,
"min": 0.00026401929785714275,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036962701699999987,
"min": 0.0036962701699999987,
"max": 0.12110386504999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010719248093664646,
"min": 0.010608972050249577,
"max": 0.5113140940666199,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1500694751739502,
"min": 0.14852561056613922,
"max": 3.5791985988616943,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 305.5,
"min": 251.26315789473685,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30550.0,
"min": 15984.0,
"max": 32950.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6344899931550025,
"min": -1.0000000521540642,
"max": 1.7121734363974723,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 163.44899931550026,
"min": -28.855601578950882,
"max": 193.47559831291437,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6344899931550025,
"min": -1.0000000521540642,
"max": 1.7121734363974723,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 163.44899931550026,
"min": -28.855601578950882,
"max": 193.47559831291437,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03374419475570903,
"min": 0.027884799392638413,
"max": 9.869934488087893,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.374419475570903,
"min": 3.150982331368141,
"max": 157.91895180940628,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1685013735",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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",
"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": "1685016026"
},
"total": 2290.7846133820003,
"count": 1,
"self": 0.47653965000017706,
"children": {
"run_training.setup": {
"total": 0.04330172199979643,
"count": 1,
"self": 0.04330172199979643
},
"TrainerController.start_learning": {
"total": 2290.2647720100003,
"count": 1,
"self": 1.3712761679344112,
"children": {
"TrainerController._reset_env": {
"total": 3.8195285570000124,
"count": 1,
"self": 3.8195285570000124
},
"TrainerController.advance": {
"total": 2284.984533540066,
"count": 64311,
"self": 1.3342490489344527,
"children": {
"env_step": {
"total": 1648.400581583092,
"count": 64311,
"self": 1540.995889020115,
"children": {
"SubprocessEnvManager._take_step": {
"total": 106.60386813292416,
"count": 64311,
"self": 4.632468123042145,
"children": {
"TorchPolicy.evaluate": {
"total": 101.97140000988202,
"count": 62565,
"self": 101.97140000988202
}
}
},
"workers": {
"total": 0.8008244300526712,
"count": 64311,
"self": 0.0,
"children": {
"worker_root": {
"total": 2285.0872638800274,
"count": 64311,
"is_parallel": true,
"self": 859.2082186989614,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017349869999634393,
"count": 1,
"is_parallel": true,
"self": 0.0005626920001304825,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011722949998329568,
"count": 8,
"is_parallel": true,
"self": 0.0011722949998329568
}
}
},
"UnityEnvironment.step": {
"total": 0.04527546899998924,
"count": 1,
"is_parallel": true,
"self": 0.0006080450002627913,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005108189998281887,
"count": 1,
"is_parallel": true,
"self": 0.0005108189998281887
},
"communicator.exchange": {
"total": 0.04245818000026702,
"count": 1,
"is_parallel": true,
"self": 0.04245818000026702
},
"steps_from_proto": {
"total": 0.0016984249996312428,
"count": 1,
"is_parallel": true,
"self": 0.0003459659988038766,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013524590008273663,
"count": 8,
"is_parallel": true,
"self": 0.0013524590008273663
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1425.879045181066,
"count": 64310,
"is_parallel": true,
"self": 31.611354539954846,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.120666307061583,
"count": 64310,
"is_parallel": true,
"self": 22.120666307061583
},
"communicator.exchange": {
"total": 1276.4288968510978,
"count": 64310,
"is_parallel": true,
"self": 1276.4288968510978
},
"steps_from_proto": {
"total": 95.71812748295179,
"count": 64310,
"is_parallel": true,
"self": 19.409465734205696,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.30866174874609,
"count": 514480,
"is_parallel": true,
"self": 76.30866174874609
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 635.2497029080396,
"count": 64311,
"self": 2.6842531729780603,
"children": {
"process_trajectory": {
"total": 108.52233872306215,
"count": 64311,
"self": 108.28878849306193,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23355023000021902,
"count": 2,
"self": 0.23355023000021902
}
}
},
"_update_policy": {
"total": 524.0431110119994,
"count": 454,
"self": 339.136625125042,
"children": {
"TorchPPOOptimizer.update": {
"total": 184.9064858869574,
"count": 22782,
"self": 184.9064858869574
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.049999789567664e-07,
"count": 1,
"self": 9.049999789567664e-07
},
"TrainerController._save_models": {
"total": 0.0894328399999722,
"count": 1,
"self": 0.0014194880004652077,
"children": {
"RLTrainer._checkpoint": {
"total": 0.088013351999507,
"count": 1,
"self": 0.088013351999507
}
}
}
}
}
}
}