ppo-Pyramid / run_logs /timers.json
s14pe's picture
First Push
7a13613 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.14686335623264313,
"min": 0.14086739718914032,
"max": 0.1524546891450882,
"count": 4
},
"Pyramids.Policy.Entropy.sum": {
"value": 4368.3037109375,
"min": 1516.8577880859375,
"max": 4615.1083984375,
"count": 4
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 234.25384615384615,
"min": 189.0612244897959,
"max": 260.2173913043478,
"count": 4
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30453.0,
"min": 9264.0,
"max": 30453.0,
"count": 4
},
"Pyramids.Step.mean": {
"value": 2099921.0,
"min": 2009927.0,
"max": 2099921.0,
"count": 4
},
"Pyramids.Step.sum": {
"value": 2099921.0,
"min": 2009927.0,
"max": 2099921.0,
"count": 4
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.8053473234176636,
"min": 0.7133234739303589,
"max": 0.8290045261383057,
"count": 4
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 244.82559204101562,
"min": 79.23908996582031,
"max": 253.67538452148438,
"count": 4
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.01725996471941471,
"min": -0.06481077522039413,
"max": 0.01725996471941471,
"count": 4
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.2470293045043945,
"min": -12.610334396362305,
"max": 5.2470293045043945,
"count": 4
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7503553699988585,
"min": 1.7207120570900112,
"max": 1.810938761550553,
"count": 4
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 227.5461980998516,
"min": 88.7359993159771,
"max": 227.5461980998516,
"count": 4
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7503553699988585,
"min": 1.7207120570900112,
"max": 1.810938761550553,
"count": 4
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 227.5461980998516,
"min": 88.7359993159771,
"max": 227.5461980998516,
"count": 4
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.018230752151878103,
"min": 0.015216292770655483,
"max": 0.02087518214358201,
"count": 4
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.3699977797441534,
"min": 0.7455983457621187,
"max": 2.421521128655513,
"count": 4
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.045669686837520984,
"min": 0.045669686837520984,
"max": 0.05387836435693316,
"count": 4
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.6393756157252938,
"min": 0.21551345742773265,
"max": 0.6912090754485689,
"count": 4
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015640732158707187,
"min": 0.01431870764686859,
"max": 0.015640732158707187,
"count": 4
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21897025022190061,
"min": 0.0590569645864889,
"max": 0.22341725134756413,
"count": 4
},
"Pyramids.Policy.LearningRate.mean": {
"value": 6.917217573571425e-07,
"min": 6.917217573571425e-07,
"max": 4.507440730750002e-06,
"count": 4
},
"Pyramids.Policy.LearningRate.sum": {
"value": 9.684104602999994e-06,
"min": 9.684104602999994e-06,
"max": 5.038434961700002e-05,
"count": 4
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.09937753979591837,
"min": 0.09594338928571429,
"max": 0.09937753979591837,
"count": 4
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.3912855571428573,
"min": 0.38377355714285716,
"max": 1.4710937142857141,
"count": 4
},
"Pyramids.Policy.Beta.mean": {
"value": 7.909308265306118e-05,
"min": 7.909308265306118e-05,
"max": 0.00046028378928571445,
"count": 4
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0011073031571428565,
"min": 0.0011073031571428565,
"max": 0.005173261700000002,
"count": 4
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00750921992585063,
"min": 0.007449968717992306,
"max": 0.007671576924622059,
"count": 4
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10512907803058624,
"min": 0.030686307698488235,
"max": 0.11174952983856201,
"count": 4
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1709849498",
"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=PyramidsTraining2 --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": "1709849813"
},
"total": 315.26667822700256,
"count": 1,
"self": 0.6019607260059274,
"children": {
"run_training.setup": {
"total": 0.06336075699800858,
"count": 1,
"self": 0.06336075699800858
},
"TrainerController.start_learning": {
"total": 314.6013567439986,
"count": 1,
"self": 0.199611276100768,
"children": {
"TrainerController._reset_env": {
"total": 2.620254447996558,
"count": 1,
"self": 2.620254447996558
},
"TrainerController.advance": {
"total": 311.6721845939028,
"count": 6653,
"self": 0.22345633607619675,
"children": {
"env_step": {
"total": 193.677894733024,
"count": 6653,
"self": 178.74847731585032,
"children": {
"SubprocessEnvManager._take_step": {
"total": 14.803519072062045,
"count": 6653,
"self": 0.523928353923111,
"children": {
"TorchPolicy.evaluate": {
"total": 14.279590718138934,
"count": 6308,
"self": 14.279590718138934
}
}
},
"workers": {
"total": 0.12589834511163644,
"count": 6653,
"self": 0.0,
"children": {
"worker_root": {
"total": 314.0457970251664,
"count": 6653,
"is_parallel": true,
"self": 149.29729433146713,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0027240900017204694,
"count": 1,
"is_parallel": true,
"self": 0.0007551800117653329,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019689099899551366,
"count": 8,
"is_parallel": true,
"self": 0.0019689099899551366
}
}
},
"UnityEnvironment.step": {
"total": 0.051165728000341915,
"count": 1,
"is_parallel": true,
"self": 0.0006359199978760444,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004655800003092736,
"count": 1,
"is_parallel": true,
"self": 0.0004655800003092736
},
"communicator.exchange": {
"total": 0.04856568800096284,
"count": 1,
"is_parallel": true,
"self": 0.04856568800096284
},
"steps_from_proto": {
"total": 0.00149854000119376,
"count": 1,
"is_parallel": true,
"self": 0.0003199400052835699,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00117859999591019,
"count": 8,
"is_parallel": true,
"self": 0.00117859999591019
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 164.74850269369927,
"count": 6652,
"is_parallel": true,
"self": 3.9677036714710994,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.036080707104702,
"count": 6652,
"is_parallel": true,
"self": 2.036080707104702
},
"communicator.exchange": {
"total": 148.8719915580623,
"count": 6652,
"is_parallel": true,
"self": 148.8719915580623
},
"steps_from_proto": {
"total": 9.872726757061173,
"count": 6652,
"is_parallel": true,
"self": 2.210711467632791,
"children": {
"_process_rank_one_or_two_observation": {
"total": 7.662015289428382,
"count": 53216,
"is_parallel": true,
"self": 7.662015289428382
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 117.77083352480258,
"count": 6653,
"self": 0.39953413871626253,
"children": {
"process_trajectory": {
"total": 13.724161448091763,
"count": 6653,
"self": 13.724161448091763
},
"_update_policy": {
"total": 103.64713793799456,
"count": 47,
"self": 34.89935663793949,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.74778130005507,
"count": 1880,
"self": 68.74778130005507
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.999988156370819e-07,
"count": 1,
"self": 7.999988156370819e-07
},
"TrainerController._save_models": {
"total": 0.10930562599969562,
"count": 1,
"self": 0.0030194499995559454,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10628617600013968,
"count": 1,
"self": 0.10628617600013968
}
}
}
}
}
}
}