ppo-Pyramids / run_logs /timers.json
Gonke's picture
First
90b1fcb verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.18705493211746216,
"min": 0.16478247940540314,
"max": 0.44203102588653564,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 5605.662109375,
"min": 4938.201171875,
"max": 12799.0361328125,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 240.1328125,
"min": 229.35245901639345,
"max": 336.12359550561797,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30737.0,
"min": 17589.0,
"max": 32323.0,
"count": 33
},
"Pyramids.Step.mean": {
"value": 1979907.0,
"min": 1019938.0,
"max": 1979907.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 1979907.0,
"min": 1019938.0,
"max": 1979907.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7753037214279175,
"min": 0.5842857956886292,
"max": 0.7826550602912903,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 234.1417236328125,
"min": 112.94467163085938,
"max": 234.1417236328125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.007218698039650917,
"min": -0.011078650131821632,
"max": 0.023848215118050575,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.180046796798706,
"min": -2.0495502948760986,
"max": 6.987526893615723,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7451243954380666,
"min": 1.5533956757956935,
"max": 1.7542524447695154,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 221.63079822063446,
"min": 108.40999849885702,
"max": 221.63079822063446,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7451243954380666,
"min": 1.5533956757956935,
"max": 1.7542524447695154,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 221.63079822063446,
"min": 108.40999849885702,
"max": 221.63079822063446,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.024534388826761254,
"min": 0.024235264870737006,
"max": 0.04270739211014271,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.1158673809986794,
"min": 2.254476272595639,
"max": 3.9742181365727447,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06661360270559921,
"min": 0.06401529681924904,
"max": 0.07187034715371694,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9325904378783889,
"min": 0.5761376713732413,
"max": 1.074378561701023,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016130074523278467,
"min": 0.013827307654967978,
"max": 0.017788065528859278,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22582104332589853,
"min": 0.141306401375914,
"max": 0.2668209829328892,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 5.160880422596431e-06,
"min": 5.160880422596431e-06,
"max": 0.00014840945053020002,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 7.225232591635003e-05,
"min": 7.225232591635003e-05,
"max": 0.0020269283743574503,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10172026071428573,
"min": 0.10172026071428573,
"max": 0.14946979999999999,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4240836500000003,
"min": 1.3452282,
"max": 2.1564575500000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00018185404535714294,
"min": 0.00018185404535714294,
"max": 0.004952033020000001,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.002545956635000001,
"min": 0.002545956635000001,
"max": 0.06763669074499999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009958143346011639,
"min": 0.008901664055883884,
"max": 0.012760956771671772,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1394140124320984,
"min": 0.11117810755968094,
"max": 0.1889527291059494,
"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": "1711997790",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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 --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1712000308"
},
"total": 2518.126583485,
"count": 1,
"self": 0.4756415490001018,
"children": {
"run_training.setup": {
"total": 0.049040627000067616,
"count": 1,
"self": 0.049040627000067616
},
"TrainerController.start_learning": {
"total": 2517.601901309,
"count": 1,
"self": 1.4609522070804815,
"children": {
"TrainerController._reset_env": {
"total": 2.0384117109997533,
"count": 1,
"self": 2.0384117109997533
},
"TrainerController.advance": {
"total": 2514.013688609919,
"count": 65417,
"self": 1.502925605067503,
"children": {
"env_step": {
"total": 1874.6336485859447,
"count": 65417,
"self": 1740.1902416718713,
"children": {
"SubprocessEnvManager._take_step": {
"total": 133.55975684108216,
"count": 65417,
"self": 4.7747069421711785,
"children": {
"TorchPolicy.evaluate": {
"total": 128.78504989891098,
"count": 62560,
"self": 128.78504989891098
}
}
},
"workers": {
"total": 0.8836500729912586,
"count": 65417,
"self": 0.0,
"children": {
"worker_root": {
"total": 2512.251911310238,
"count": 65417,
"is_parallel": true,
"self": 898.011206602202,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022879790003571543,
"count": 1,
"is_parallel": true,
"self": 0.0006465400010711164,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016414389992860379,
"count": 8,
"is_parallel": true,
"self": 0.0016414389992860379
}
}
},
"UnityEnvironment.step": {
"total": 0.05712476000007882,
"count": 1,
"is_parallel": true,
"self": 0.0032920459989327355,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004432969999470515,
"count": 1,
"is_parallel": true,
"self": 0.0004432969999470515
},
"communicator.exchange": {
"total": 0.05172769400087418,
"count": 1,
"is_parallel": true,
"self": 0.05172769400087418
},
"steps_from_proto": {
"total": 0.001661723000324855,
"count": 1,
"is_parallel": true,
"self": 0.0003732569985004375,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012884660018244176,
"count": 8,
"is_parallel": true,
"self": 0.0012884660018244176
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1614.240704708036,
"count": 65416,
"is_parallel": true,
"self": 34.801910062221395,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.99356799708312,
"count": 65416,
"is_parallel": true,
"self": 24.99356799708312
},
"communicator.exchange": {
"total": 1451.0625788657353,
"count": 65416,
"is_parallel": true,
"self": 1451.0625788657353
},
"steps_from_proto": {
"total": 103.38264778299617,
"count": 65416,
"is_parallel": true,
"self": 21.307672516118146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.07497526687803,
"count": 523328,
"is_parallel": true,
"self": 82.07497526687803
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 637.8771144189068,
"count": 65417,
"self": 2.9310192950533747,
"children": {
"process_trajectory": {
"total": 135.03107008984261,
"count": 65417,
"self": 134.81534168884173,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21572840100088797,
"count": 2,
"self": 0.21572840100088797
}
}
},
"_update_policy": {
"total": 499.9150250340108,
"count": 472,
"self": 294.54177497197907,
"children": {
"TorchPPOOptimizer.update": {
"total": 205.37325006203173,
"count": 22713,
"self": 205.37325006203173
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.400002116104588e-07,
"count": 1,
"self": 8.400002116104588e-07
},
"TrainerController._save_models": {
"total": 0.08884794100049476,
"count": 1,
"self": 0.0018642500008354546,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0869836909996593,
"count": 1,
"self": 0.0869836909996593
}
}
}
}
}
}
}