ppo-Huggy / run_logs /timers.json
TootToot's picture
Huggy
5a64b34
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3996235132217407,
"min": 1.3996235132217407,
"max": 1.4283359050750732,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69827.21875,
"min": 68443.4375,
"max": 77023.0078125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.47797716150082,
"min": 80.47797716150082,
"max": 401.6825396825397,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49333.0,
"min": 49157.0,
"max": 50612.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999906.0,
"min": 49988.0,
"max": 1999906.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999906.0,
"min": 49988.0,
"max": 1999906.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.385777473449707,
"min": 0.009915120899677277,
"max": 2.430847644805908,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1462.4815673828125,
"min": 1.2393901348114014,
"max": 1462.4815673828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.647996749224515,
"min": 1.9233169865608215,
"max": 3.8755954584141947,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2236.2220072746277,
"min": 240.4146233201027,
"max": 2236.2220072746277,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.647996749224515,
"min": 1.9233169865608215,
"max": 3.8755954584141947,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2236.2220072746277,
"min": 240.4146233201027,
"max": 2236.2220072746277,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014439888263586907,
"min": 0.013108634809678837,
"max": 0.021196249868565546,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.028879776527173814,
"min": 0.02645938691130141,
"max": 0.057462945113366,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06863893251866102,
"min": 0.022788701392710206,
"max": 0.06882662878682216,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.13727786503732203,
"min": 0.04557740278542041,
"max": 0.19475689940154553,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.459073513674998e-06,
"min": 4.459073513674998e-06,
"max": 0.00029528970157010004,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.918147027349996e-06,
"min": 8.918147027349996e-06,
"max": 0.00084357466880845,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101486325,
"min": 0.101486325,
"max": 0.1984299,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20297265,
"min": 0.20297265,
"max": 0.58119155,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.416761749999997e-05,
"min": 8.416761749999997e-05,
"max": 0.00492165201,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016833523499999994,
"min": 0.00016833523499999994,
"max": 0.014061458345,
"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": "1688395922",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1688398281"
},
"total": 2358.6050041510002,
"count": 1,
"self": 0.43864498500033733,
"children": {
"run_training.setup": {
"total": 0.043092682000065,
"count": 1,
"self": 0.043092682000065
},
"TrainerController.start_learning": {
"total": 2358.123266484,
"count": 1,
"self": 4.171306707058648,
"children": {
"TrainerController._reset_env": {
"total": 4.10922480499994,
"count": 1,
"self": 4.10922480499994
},
"TrainerController.advance": {
"total": 2349.7315278719416,
"count": 231917,
"self": 4.388288699918121,
"children": {
"env_step": {
"total": 1835.5190091201075,
"count": 231917,
"self": 1546.0329148400522,
"children": {
"SubprocessEnvManager._take_step": {
"total": 286.8296068860244,
"count": 231917,
"self": 16.348750633011832,
"children": {
"TorchPolicy.evaluate": {
"total": 270.4808562530126,
"count": 222882,
"self": 270.4808562530126
}
}
},
"workers": {
"total": 2.6564873940309326,
"count": 231917,
"self": 0.0,
"children": {
"worker_root": {
"total": 2350.545042976117,
"count": 231917,
"is_parallel": true,
"self": 1085.682557866081,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008917809999502424,
"count": 1,
"is_parallel": true,
"self": 0.0002753239999719881,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006164569999782543,
"count": 2,
"is_parallel": true,
"self": 0.0006164569999782543
}
}
},
"UnityEnvironment.step": {
"total": 0.02835647599999902,
"count": 1,
"is_parallel": true,
"self": 0.00031673499995577004,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002383620000045994,
"count": 1,
"is_parallel": true,
"self": 0.0002383620000045994
},
"communicator.exchange": {
"total": 0.02707606300009502,
"count": 1,
"is_parallel": true,
"self": 0.02707606300009502
},
"steps_from_proto": {
"total": 0.000725315999943632,
"count": 1,
"is_parallel": true,
"self": 0.00021000799995363195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005153079999900001,
"count": 2,
"is_parallel": true,
"self": 0.0005153079999900001
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1264.8624851100362,
"count": 231916,
"is_parallel": true,
"self": 39.275736042906146,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.83619503009243,
"count": 231916,
"is_parallel": true,
"self": 78.83619503009243
},
"communicator.exchange": {
"total": 1052.4197886509828,
"count": 231916,
"is_parallel": true,
"self": 1052.4197886509828
},
"steps_from_proto": {
"total": 94.33076538605496,
"count": 231916,
"is_parallel": true,
"self": 33.390641049996475,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.94012433605849,
"count": 463832,
"is_parallel": true,
"self": 60.94012433605849
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 509.8242300519157,
"count": 231917,
"self": 6.384156880928458,
"children": {
"process_trajectory": {
"total": 131.67724607898367,
"count": 231917,
"self": 130.32106857398344,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3561775050002325,
"count": 10,
"self": 1.3561775050002325
}
}
},
"_update_policy": {
"total": 371.7628270920036,
"count": 96,
"self": 313.0295590090092,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.733268082994414,
"count": 2880,
"self": 58.733268082994414
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.089996299531776e-07,
"count": 1,
"self": 8.089996299531776e-07
},
"TrainerController._save_models": {
"total": 0.11120629100014412,
"count": 1,
"self": 0.0019907540004169277,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10921553699972719,
"count": 1,
"self": 0.10921553699972719
}
}
}
}
}
}
}