ppo-Huggy1 / run_logs /timers.json
Orokusaki's picture
Huggy
f0cc2b3
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4082770347595215,
"min": 1.4082770347595215,
"max": 1.4252370595932007,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71156.015625,
"min": 69182.46875,
"max": 76089.2265625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 68.31666666666666,
"min": 67.53761969904241,
"max": 425.02542372881356,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49188.0,
"min": 49070.0,
"max": 50174.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999909.0,
"min": 49977.0,
"max": 1999909.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999909.0,
"min": 49977.0,
"max": 1999909.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.489823818206787,
"min": 0.014062084257602692,
"max": 2.5486245155334473,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1795.1629638671875,
"min": 1.645263910293579,
"max": 1799.543212890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9684839733926665,
"min": 1.8956961629227695,
"max": 4.1138239511287065,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2861.2769448161125,
"min": 221.79645106196404,
"max": 2861.2769448161125,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9684839733926665,
"min": 1.8956961629227695,
"max": 4.1138239511287065,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2861.2769448161125,
"min": 221.79645106196404,
"max": 2861.2769448161125,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015467956511484873,
"min": 0.01265818692772882,
"max": 0.019691824303299653,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04640386953445462,
"min": 0.02531637385545764,
"max": 0.056605601295693,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.061468028442727196,
"min": 0.022448101515571278,
"max": 0.06347012830277284,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1844040853281816,
"min": 0.044896203031142556,
"max": 0.19041038490831852,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.76304874568333e-06,
"min": 3.76304874568333e-06,
"max": 0.0002953464015511999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1289146237049991e-05,
"min": 1.1289146237049991e-05,
"max": 0.00084415486861505,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125431666666666,
"min": 0.10125431666666666,
"max": 0.19844879999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30376295,
"min": 0.20764644999999998,
"max": 0.5813849500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.259040166666664e-05,
"min": 7.259040166666664e-05,
"max": 0.00492259512,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021777120499999993,
"min": 0.00021777120499999993,
"max": 0.014071109005,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1671570445",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy1 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1671572719"
},
"total": 2273.888326046,
"count": 1,
"self": 0.4408888390003085,
"children": {
"run_training.setup": {
"total": 0.10195406399998319,
"count": 1,
"self": 0.10195406399998319
},
"TrainerController.start_learning": {
"total": 2273.345483143,
"count": 1,
"self": 3.9590827859542514,
"children": {
"TrainerController._reset_env": {
"total": 7.287745845000018,
"count": 1,
"self": 7.287745845000018
},
"TrainerController.advance": {
"total": 2261.980574465046,
"count": 233312,
"self": 4.220398857939472,
"children": {
"env_step": {
"total": 1782.5646325291113,
"count": 233312,
"self": 1499.3702498822,
"children": {
"SubprocessEnvManager._take_step": {
"total": 280.4882445489086,
"count": 233312,
"self": 14.711054678798519,
"children": {
"TorchPolicy.evaluate": {
"total": 265.7771898701101,
"count": 222938,
"self": 66.61857835111368,
"children": {
"TorchPolicy.sample_actions": {
"total": 199.1586115189964,
"count": 222938,
"self": 199.1586115189964
}
}
}
}
},
"workers": {
"total": 2.706138098002839,
"count": 233312,
"self": 0.0,
"children": {
"worker_root": {
"total": 2265.1961664889104,
"count": 233312,
"is_parallel": true,
"self": 1032.7852006899338,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020507649999785826,
"count": 1,
"is_parallel": true,
"self": 0.000328539999941313,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017222250000372696,
"count": 2,
"is_parallel": true,
"self": 0.0017222250000372696
}
}
},
"UnityEnvironment.step": {
"total": 0.02922412599997415,
"count": 1,
"is_parallel": true,
"self": 0.00027067699994631766,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021032500001183507,
"count": 1,
"is_parallel": true,
"self": 0.00021032500001183507
},
"communicator.exchange": {
"total": 0.02798820399999613,
"count": 1,
"is_parallel": true,
"self": 0.02798820399999613
},
"steps_from_proto": {
"total": 0.0007549200000198653,
"count": 1,
"is_parallel": true,
"self": 0.00028483600004847176,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004700839999713935,
"count": 2,
"is_parallel": true,
"self": 0.0004700839999713935
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1232.4109657989766,
"count": 233311,
"is_parallel": true,
"self": 34.398787314040874,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.54548614987738,
"count": 233311,
"is_parallel": true,
"self": 80.54548614987738
},
"communicator.exchange": {
"total": 1021.319269574024,
"count": 233311,
"is_parallel": true,
"self": 1021.319269574024
},
"steps_from_proto": {
"total": 96.1474227610343,
"count": 233311,
"is_parallel": true,
"self": 41.83016988814808,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.31725287288623,
"count": 466622,
"is_parallel": true,
"self": 54.31725287288623
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 475.19554307799524,
"count": 233312,
"self": 6.035829852068332,
"children": {
"process_trajectory": {
"total": 155.6843744819264,
"count": 233312,
"self": 154.51929626592664,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1650782159997561,
"count": 10,
"self": 1.1650782159997561
}
}
},
"_update_policy": {
"total": 313.4753387440005,
"count": 97,
"self": 261.5324889680064,
"children": {
"TorchPPOOptimizer.update": {
"total": 51.94284977599409,
"count": 2910,
"self": 51.94284977599409
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.479999789618887e-07,
"count": 1,
"self": 9.479999789618887e-07
},
"TrainerController._save_models": {
"total": 0.11807909899971492,
"count": 1,
"self": 0.002402315999916027,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11567678299979889,
"count": 1,
"self": 0.11567678299979889
}
}
}
}
}
}
}