ppo-Huggy / run_logs /timers.json
ziemke's picture
Huggy
e113133
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3992245197296143,
"min": 1.3992245197296143,
"max": 1.4268728494644165,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69379.1484375,
"min": 68801.203125,
"max": 76809.0078125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.19736842105263,
"min": 78.34231378763867,
"max": 379.67424242424244,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49368.0,
"min": 49300.0,
"max": 50151.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999995.0,
"min": 49897.0,
"max": 1999995.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999995.0,
"min": 49897.0,
"max": 1999995.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4417014122009277,
"min": 0.14388029277324677,
"max": 2.4768049716949463,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1484.554443359375,
"min": 18.848318099975586,
"max": 1524.427001953125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8499598540365696,
"min": 1.6956584894930133,
"max": 3.9831891561178137,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2340.7755912542343,
"min": 222.13126212358475,
"max": 2402.2361992001534,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8499598540365696,
"min": 1.6956584894930133,
"max": 3.9831891561178137,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2340.7755912542343,
"min": 222.13126212358475,
"max": 2402.2361992001534,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019585547404777675,
"min": 0.01415118840438178,
"max": 0.020640809178197134,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05875664221433302,
"min": 0.02830237680876356,
"max": 0.05875664221433302,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06029735687706206,
"min": 0.02277940365796288,
"max": 0.06029735687706206,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18089207063118617,
"min": 0.04555880731592576,
"max": 0.18089207063118617,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6529487823833416e-06,
"min": 3.6529487823833416e-06,
"max": 0.0002953647015451,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0958846347150024e-05,
"min": 1.0958846347150024e-05,
"max": 0.0008441625186125,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121761666666669,
"min": 0.10121761666666669,
"max": 0.19845489999999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036528500000001,
"min": 0.20756630000000004,
"max": 0.5813875000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.07590716666668e-05,
"min": 7.07590716666668e-05,
"max": 0.00492289951,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002122772150000004,
"min": 0.0002122772150000004,
"max": 0.01407123625,
"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": "1670940258",
"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=Huggy --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": "1670942970"
},
"total": 2711.96187575,
"count": 1,
"self": 0.4498265380002522,
"children": {
"run_training.setup": {
"total": 0.1236724700000309,
"count": 1,
"self": 0.1236724700000309
},
"TrainerController.start_learning": {
"total": 2711.3883767419998,
"count": 1,
"self": 5.495645921996129,
"children": {
"TrainerController._reset_env": {
"total": 11.804119817000014,
"count": 1,
"self": 11.804119817000014
},
"TrainerController.advance": {
"total": 2693.9597241670035,
"count": 232633,
"self": 5.3568525649816365,
"children": {
"env_step": {
"total": 2163.381585111976,
"count": 232633,
"self": 1816.7419314640224,
"children": {
"SubprocessEnvManager._take_step": {
"total": 342.9171474059461,
"count": 232633,
"self": 18.64837650496247,
"children": {
"TorchPolicy.evaluate": {
"total": 324.2687709009836,
"count": 222859,
"self": 83.18549692417412,
"children": {
"TorchPolicy.sample_actions": {
"total": 241.0832739768095,
"count": 222859,
"self": 241.0832739768095
}
}
}
}
},
"workers": {
"total": 3.7225062420076256,
"count": 232633,
"self": 0.0,
"children": {
"worker_root": {
"total": 2700.940487930952,
"count": 232633,
"is_parallel": true,
"self": 1213.720131062865,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021753309999894554,
"count": 1,
"is_parallel": true,
"self": 0.00031589700000722587,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018594339999822296,
"count": 2,
"is_parallel": true,
"self": 0.0018594339999822296
}
}
},
"UnityEnvironment.step": {
"total": 0.030153307999967183,
"count": 1,
"is_parallel": true,
"self": 0.00031462899994494364,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019323000003623747,
"count": 1,
"is_parallel": true,
"self": 0.00019323000003623747
},
"communicator.exchange": {
"total": 0.028823177999981908,
"count": 1,
"is_parallel": true,
"self": 0.028823177999981908
},
"steps_from_proto": {
"total": 0.0008222710000040934,
"count": 1,
"is_parallel": true,
"self": 0.0002683949999777724,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000553876000026321,
"count": 2,
"is_parallel": true,
"self": 0.000553876000026321
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1487.2203568680868,
"count": 232632,
"is_parallel": true,
"self": 42.46413502711266,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.22057064499768,
"count": 232632,
"is_parallel": true,
"self": 85.22057064499768
},
"communicator.exchange": {
"total": 1245.4479883960325,
"count": 232632,
"is_parallel": true,
"self": 1245.4479883960325
},
"steps_from_proto": {
"total": 114.08766279994393,
"count": 232632,
"is_parallel": true,
"self": 45.75449949995647,
"children": {
"_process_rank_one_or_two_observation": {
"total": 68.33316329998746,
"count": 465264,
"is_parallel": true,
"self": 68.33316329998746
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 525.2212864900457,
"count": 232633,
"self": 8.853335223083377,
"children": {
"process_trajectory": {
"total": 170.87935383396257,
"count": 232633,
"self": 170.3730628189628,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5062910149997606,
"count": 4,
"self": 0.5062910149997606
}
}
},
"_update_policy": {
"total": 345.48859743299977,
"count": 97,
"self": 287.0668850259875,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.42171240701225,
"count": 2910,
"self": 58.42171240701225
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.350001164420974e-07,
"count": 1,
"self": 9.350001164420974e-07
},
"TrainerController._save_models": {
"total": 0.12888590100010333,
"count": 1,
"self": 0.0021002829998906236,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1267856180002127,
"count": 1,
"self": 0.1267856180002127
}
}
}
}
}
}
}