ppo-Huggy / run_logs /timers.json
PhilSad's picture
Huggy
a13d89e
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4089080095291138,
"min": 1.4089080095291138,
"max": 1.4291564226150513,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70511.6171875,
"min": 66593.171875,
"max": 79502.6171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.90814558058925,
"min": 77.78740157480316,
"max": 407.7560975609756,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49569.0,
"min": 49002.0,
"max": 50209.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999487.0,
"min": 49636.0,
"max": 1999487.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999487.0,
"min": 49636.0,
"max": 1999487.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4393749237060547,
"min": -0.01533165480941534,
"max": 2.470686674118042,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1407.519287109375,
"min": -1.8704619407653809,
"max": 1528.344970703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.743876143799291,
"min": 2.0283383179883487,
"max": 4.0108153150715955,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2160.216534972191,
"min": 247.45727479457855,
"max": 2413.4655570983887,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.743876143799291,
"min": 2.0283383179883487,
"max": 4.0108153150715955,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2160.216534972191,
"min": 247.45727479457855,
"max": 2413.4655570983887,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018091338386875575,
"min": 0.013215166706423689,
"max": 0.019788699158622573,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05427401516062673,
"min": 0.02764100633212365,
"max": 0.05427401516062673,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054335582007964456,
"min": 0.02275278658295671,
"max": 0.0604300107806921,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16300674602389337,
"min": 0.04550557316591342,
"max": 0.17546747115751107,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4854488382166647e-06,
"min": 3.4854488382166647e-06,
"max": 0.00029528602657132497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0456346514649995e-05,
"min": 1.0456346514649995e-05,
"max": 0.0008441997186000999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116178333333332,
"min": 0.10116178333333332,
"max": 0.19842867500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30348535,
"min": 0.20745035000000006,
"max": 0.5813999000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.797298833333331e-05,
"min": 6.797298833333331e-05,
"max": 0.004921590882500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020391896499999995,
"min": 0.00020391896499999995,
"max": 0.014071855010000002,
"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": "1679002512",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679004818"
},
"total": 2306.0445212289997,
"count": 1,
"self": 0.43955186999937723,
"children": {
"run_training.setup": {
"total": 0.17041557700008525,
"count": 1,
"self": 0.17041557700008525
},
"TrainerController.start_learning": {
"total": 2305.434553782,
"count": 1,
"self": 4.253189511080109,
"children": {
"TrainerController._reset_env": {
"total": 8.735925886000018,
"count": 1,
"self": 8.735925886000018
},
"TrainerController.advance": {
"total": 2292.3257042839195,
"count": 232727,
"self": 4.555545827935475,
"children": {
"env_step": {
"total": 1778.6863203919766,
"count": 232727,
"self": 1500.0905694889793,
"children": {
"SubprocessEnvManager._take_step": {
"total": 275.8138016620163,
"count": 232727,
"self": 16.425121856074497,
"children": {
"TorchPolicy.evaluate": {
"total": 259.3886798059418,
"count": 222946,
"self": 259.3886798059418
}
}
},
"workers": {
"total": 2.781949240981021,
"count": 232727,
"self": 0.0,
"children": {
"worker_root": {
"total": 2297.5708252570967,
"count": 232727,
"is_parallel": true,
"self": 1081.664954685071,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011626579999983733,
"count": 1,
"is_parallel": true,
"self": 0.00031420400000570226,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000848453999992671,
"count": 2,
"is_parallel": true,
"self": 0.000848453999992671
}
}
},
"UnityEnvironment.step": {
"total": 0.02792232399997374,
"count": 1,
"is_parallel": true,
"self": 0.00030956299997342285,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021590000005744514,
"count": 1,
"is_parallel": true,
"self": 0.00021590000005744514
},
"communicator.exchange": {
"total": 0.026739479999946525,
"count": 1,
"is_parallel": true,
"self": 0.026739479999946525
},
"steps_from_proto": {
"total": 0.0006573809999963487,
"count": 1,
"is_parallel": true,
"self": 0.00019747300007111335,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00045990799992523534,
"count": 2,
"is_parallel": true,
"self": 0.00045990799992523534
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1215.9058705720256,
"count": 232726,
"is_parallel": true,
"self": 37.509193685132004,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 74.99483965098557,
"count": 232726,
"is_parallel": true,
"self": 74.99483965098557
},
"communicator.exchange": {
"total": 1016.1262674779234,
"count": 232726,
"is_parallel": true,
"self": 1016.1262674779234
},
"steps_from_proto": {
"total": 87.27556975798461,
"count": 232726,
"is_parallel": true,
"self": 32.519898450841765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.75567130714285,
"count": 465452,
"is_parallel": true,
"self": 54.75567130714285
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 509.0838380640074,
"count": 232727,
"self": 6.567556687107185,
"children": {
"process_trajectory": {
"total": 142.33433128490026,
"count": 232727,
"self": 140.8786152808999,
"children": {
"RLTrainer._checkpoint": {
"total": 1.455716004000351,
"count": 10,
"self": 1.455716004000351
}
}
},
"_update_policy": {
"total": 360.18195009199997,
"count": 97,
"self": 302.3260385359964,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.85591155600355,
"count": 2910,
"self": 57.85591155600355
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0060002750833519e-06,
"count": 1,
"self": 1.0060002750833519e-06
},
"TrainerController._save_models": {
"total": 0.11973309499990137,
"count": 1,
"self": 0.0020752539999193687,
"children": {
"RLTrainer._checkpoint": {
"total": 0.117657840999982,
"count": 1,
"self": 0.117657840999982
}
}
}
}
}
}
}