ppo-Huggy / run_logs /timers.json
apple9855's picture
Huggy
87025ad verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4055659770965576,
"min": 1.4055659770965576,
"max": 1.4288665056228638,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71399.9375,
"min": 66868.359375,
"max": 78821.40625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.95667870036101,
"min": 86.91739894551846,
"max": 400.896,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48728.0,
"min": 48728.0,
"max": 50157.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999990.0,
"min": 49756.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999990.0,
"min": 49756.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3658769130706787,
"min": 0.08568933606147766,
"max": 2.444106340408325,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1310.69580078125,
"min": 10.62547779083252,
"max": 1363.4642333984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7025208443080477,
"min": 1.725976332541435,
"max": 3.9099900308548796,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2051.1965477466583,
"min": 214.02106523513794,
"max": 2170.1648183465004,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7025208443080477,
"min": 1.725976332541435,
"max": 3.9099900308548796,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2051.1965477466583,
"min": 214.02106523513794,
"max": 2170.1648183465004,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016132627754996066,
"min": 0.012799102639473859,
"max": 0.018876858987884285,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0483978832649882,
"min": 0.025598205278947718,
"max": 0.05629676265501378,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05643235366377566,
"min": 0.022642581289013225,
"max": 0.06376033338407676,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16929706099132696,
"min": 0.0461540350690484,
"max": 0.19128100015223026,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.249548916849998e-06,
"min": 3.249548916849998e-06,
"max": 0.000295270426576525,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.748646750549993e-06,
"min": 9.748646750549993e-06,
"max": 0.0008438842687052497,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108315000000001,
"min": 0.10108315000000001,
"max": 0.19842347499999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30324945000000003,
"min": 0.20729615,
"max": 0.5812947500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.404918499999998e-05,
"min": 6.404918499999998e-05,
"max": 0.0049213314025,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001921475549999999,
"min": 0.0001921475549999999,
"max": 0.014066608024999998,
"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": "1725244182",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1725246735"
},
"total": 2552.7270435970004,
"count": 1,
"self": 0.42642889200033096,
"children": {
"run_training.setup": {
"total": 0.05581392199997026,
"count": 1,
"self": 0.05581392199997026
},
"TrainerController.start_learning": {
"total": 2552.244800783,
"count": 1,
"self": 4.6032239549927,
"children": {
"TrainerController._reset_env": {
"total": 2.122003536999955,
"count": 1,
"self": 2.122003536999955
},
"TrainerController.advance": {
"total": 2545.405254815007,
"count": 231924,
"self": 4.696812130071521,
"children": {
"env_step": {
"total": 2028.603618130019,
"count": 231924,
"self": 1597.229609914862,
"children": {
"SubprocessEnvManager._take_step": {
"total": 428.4341507340796,
"count": 231924,
"self": 16.249335518087832,
"children": {
"TorchPolicy.evaluate": {
"total": 412.18481521599176,
"count": 223060,
"self": 412.18481521599176
}
}
},
"workers": {
"total": 2.939857481077297,
"count": 231924,
"self": 0.0,
"children": {
"worker_root": {
"total": 2544.8094749398824,
"count": 231924,
"is_parallel": true,
"self": 1253.4441510949314,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008584850000943334,
"count": 1,
"is_parallel": true,
"self": 0.0002356070001496846,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006228779999446488,
"count": 2,
"is_parallel": true,
"self": 0.0006228779999446488
}
}
},
"UnityEnvironment.step": {
"total": 0.031834294000077534,
"count": 1,
"is_parallel": true,
"self": 0.0004114949999802775,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002741280000009283,
"count": 1,
"is_parallel": true,
"self": 0.0002741280000009283
},
"communicator.exchange": {
"total": 0.030354560000091624,
"count": 1,
"is_parallel": true,
"self": 0.030354560000091624
},
"steps_from_proto": {
"total": 0.0007941110000047047,
"count": 1,
"is_parallel": true,
"self": 0.00019404499994379876,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006000660000609059,
"count": 2,
"is_parallel": true,
"self": 0.0006000660000609059
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1291.365323844951,
"count": 231923,
"is_parallel": true,
"self": 39.061273421928945,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.03284230092561,
"count": 231923,
"is_parallel": true,
"self": 86.03284230092561
},
"communicator.exchange": {
"total": 1072.773368308,
"count": 231923,
"is_parallel": true,
"self": 1072.773368308
},
"steps_from_proto": {
"total": 93.49783981409644,
"count": 231923,
"is_parallel": true,
"self": 35.02419240611175,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.473647407984686,
"count": 463846,
"is_parallel": true,
"self": 58.473647407984686
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 512.1048245549166,
"count": 231924,
"self": 7.080351497952847,
"children": {
"process_trajectory": {
"total": 162.73916322296634,
"count": 231924,
"self": 161.09180165796658,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6473615649997555,
"count": 10,
"self": 1.6473615649997555
}
}
},
"_update_policy": {
"total": 342.2853098339974,
"count": 97,
"self": 275.1004328219991,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.18487701199831,
"count": 2910,
"self": 67.18487701199831
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2010000318696257e-06,
"count": 1,
"self": 1.2010000318696257e-06
},
"TrainerController._save_models": {
"total": 0.11431727499984845,
"count": 1,
"self": 0.0017950069996004459,
"children": {
"RLTrainer._checkpoint": {
"total": 0.112522268000248,
"count": 1,
"self": 0.112522268000248
}
}
}
}
}
}
}