lambdt's picture
First commit
74e8caa verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.6525681614875793,
"min": 0.6525681614875793,
"max": 1.533087134361267,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 19556.162109375,
"min": 19556.162109375,
"max": 46507.73046875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989979.0,
"min": 29952.0,
"max": 989979.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989979.0,
"min": 29952.0,
"max": 989979.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3954375386238098,
"min": -0.10736285150051117,
"max": 0.4441004693508148,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 104.3955078125,
"min": -25.874446868896484,
"max": 119.9071273803711,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.014385219663381577,
"min": -0.00144211167935282,
"max": 0.23993141949176788,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.7976980209350586,
"min": -0.379275381565094,
"max": 56.863746643066406,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06658644933783102,
"min": 0.06507835995975923,
"max": 0.07367795165147431,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9987967400674653,
"min": 0.495943588506425,
"max": 1.0621000398755047,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013017619441467296,
"min": 0.00034362005199891304,
"max": 0.013704449782666167,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19526429162200945,
"min": 0.0037798205719880434,
"max": 0.19526429162200945,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.514057495346667e-06,
"min": 7.514057495346667e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001127108624302,
"min": 0.0001127108624302,
"max": 0.0032574833141722987,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025046533333333,
"min": 0.1025046533333333,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5375697999999995,
"min": 1.3691136000000002,
"max": 2.443067,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000260214868,
"min": 0.000260214868,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00390322302,
"min": 0.00390322302,
"max": 0.10860418723000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007025709841400385,
"min": 0.007025709841400385,
"max": 0.31110304594039917,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10538564622402191,
"min": 0.10331598669290543,
"max": 2.1777212619781494,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 494.3015873015873,
"min": 439.6333333333333,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31141.0,
"min": 15984.0,
"max": 33390.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.3469269567775348,
"min": -1.0000000521540642,
"max": 1.4603299785405397,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 84.85639827698469,
"min": -32.000001668930054,
"max": 98.5843983516097,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.3469269567775348,
"min": -1.0000000521540642,
"max": 1.4603299785405397,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 84.85639827698469,
"min": -32.000001668930054,
"max": 98.5843983516097,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03650491859494535,
"min": 0.03353248922212515,
"max": 6.5191537123173475,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.299809871481557,
"min": 2.1125468209938845,
"max": 104.30645939707756,
"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": "1767510969",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1767513077"
},
"total": 2107.2404090829996,
"count": 1,
"self": 0.49525218299959306,
"children": {
"run_training.setup": {
"total": 0.02299962000006417,
"count": 1,
"self": 0.02299962000006417
},
"TrainerController.start_learning": {
"total": 2106.72215728,
"count": 1,
"self": 1.390190881989838,
"children": {
"TrainerController._reset_env": {
"total": 2.1264326420000543,
"count": 1,
"self": 2.1264326420000543
},
"TrainerController.advance": {
"total": 2103.13313811101,
"count": 63446,
"self": 1.4134600750176105,
"children": {
"env_step": {
"total": 1459.003464959962,
"count": 63446,
"self": 1312.9902604640101,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.17340375793174,
"count": 63446,
"self": 4.447354966951025,
"children": {
"TorchPolicy.evaluate": {
"total": 140.7260487909807,
"count": 62554,
"self": 140.7260487909807
}
}
},
"workers": {
"total": 0.8398007380201307,
"count": 63446,
"self": 0.0,
"children": {
"worker_root": {
"total": 2100.2289324470044,
"count": 63446,
"is_parallel": true,
"self": 901.4884438240331,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017261959999359533,
"count": 1,
"is_parallel": true,
"self": 0.0005492930004038499,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011769029995321034,
"count": 8,
"is_parallel": true,
"self": 0.0011769029995321034
}
}
},
"UnityEnvironment.step": {
"total": 0.05054545400003008,
"count": 1,
"is_parallel": true,
"self": 0.0005472049997479189,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004334350001045095,
"count": 1,
"is_parallel": true,
"self": 0.0004334350001045095
},
"communicator.exchange": {
"total": 0.04790249500001664,
"count": 1,
"is_parallel": true,
"self": 0.04790249500001664
},
"steps_from_proto": {
"total": 0.0016623190001610055,
"count": 1,
"is_parallel": true,
"self": 0.00033165399986501143,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001330665000295994,
"count": 8,
"is_parallel": true,
"self": 0.001330665000295994
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1198.7404886229713,
"count": 63445,
"is_parallel": true,
"self": 32.89813059500193,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.223536424000713,
"count": 63445,
"is_parallel": true,
"self": 22.223536424000713
},
"communicator.exchange": {
"total": 1041.6474980519338,
"count": 63445,
"is_parallel": true,
"self": 1041.6474980519338
},
"steps_from_proto": {
"total": 101.97132355203485,
"count": 63445,
"is_parallel": true,
"self": 21.54097453214399,
"children": {
"_process_rank_one_or_two_observation": {
"total": 80.43034901989085,
"count": 507560,
"is_parallel": true,
"self": 80.43034901989085
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 642.7162130760303,
"count": 63446,
"self": 2.680251155037695,
"children": {
"process_trajectory": {
"total": 119.75628736999056,
"count": 63446,
"self": 119.5802175739907,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17606979599986516,
"count": 2,
"self": 0.17606979599986516
}
}
},
"_update_policy": {
"total": 520.279674551002,
"count": 445,
"self": 291.0864240089968,
"children": {
"TorchPPOOptimizer.update": {
"total": 229.19325054200522,
"count": 22800,
"self": 229.19325054200522
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.560000424040481e-07,
"count": 1,
"self": 8.560000424040481e-07
},
"TrainerController._save_models": {
"total": 0.07239478900009999,
"count": 1,
"self": 0.0010229460003756685,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07137184299972432,
"count": 1,
"self": 0.07137184299972432
}
}
}
}
}
}
}