ppo-Huggy / run_logs /timers.json
Nurmukhamed's picture
Huggy
abc5a18
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3998900651931763,
"min": 1.3998900651931763,
"max": 1.4216424226760864,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69018.78125,
"min": 68328.671875,
"max": 75964.2890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 95.43050193050193,
"min": 89.16216216216216,
"max": 425.6694915254237,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49433.0,
"min": 48894.0,
"max": 50229.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999888.0,
"min": 49933.0,
"max": 1999888.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999888.0,
"min": 49933.0,
"max": 1999888.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.391500949859619,
"min": 0.008275721222162247,
"max": 2.436175584793091,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1238.7974853515625,
"min": 0.9682593941688538,
"max": 1330.833740234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5762259469989646,
"min": 1.7914368306469715,
"max": 3.85586224160951,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1852.4850405454636,
"min": 209.59810918569565,
"max": 2089.8773349523544,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5762259469989646,
"min": 1.7914368306469715,
"max": 3.85586224160951,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1852.4850405454636,
"min": 209.59810918569565,
"max": 2089.8773349523544,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016589286064360446,
"min": 0.012935366085730492,
"max": 0.02097097523140595,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03317857212872089,
"min": 0.025870732171460985,
"max": 0.06281346191074892,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.050658928168316686,
"min": 0.022335940940926474,
"max": 0.05950170749177536,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10131785633663337,
"min": 0.04467188188185295,
"max": 0.16902212599913277,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.614323461925001e-06,
"min": 4.614323461925001e-06,
"max": 0.0002953356015548,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.228646923850002e-06,
"min": 9.228646923850002e-06,
"max": 0.0008438103187299001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10153807500000003,
"min": 0.10153807500000003,
"max": 0.19844520000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20307615000000007,
"min": 0.20307615000000007,
"max": 0.5812700999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.674994249999998e-05,
"min": 8.674994249999998e-05,
"max": 0.004922415480000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017349988499999996,
"min": 0.00017349988499999996,
"max": 0.014065377989999999,
"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": "1692759144",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=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": "1692761868"
},
"total": 2723.9740796120004,
"count": 1,
"self": 0.845816503000151,
"children": {
"run_training.setup": {
"total": 0.04631843800007118,
"count": 1,
"self": 0.04631843800007118
},
"TrainerController.start_learning": {
"total": 2723.081944671,
"count": 1,
"self": 5.628755233989068,
"children": {
"TrainerController._reset_env": {
"total": 5.669066942999962,
"count": 1,
"self": 5.669066942999962
},
"TrainerController.advance": {
"total": 2711.5878682310113,
"count": 231917,
"self": 5.704071492880757,
"children": {
"env_step": {
"total": 2105.751950060061,
"count": 231917,
"self": 1772.5885059372167,
"children": {
"SubprocessEnvManager._take_step": {
"total": 329.55908772686143,
"count": 231917,
"self": 18.755970522860252,
"children": {
"TorchPolicy.evaluate": {
"total": 310.8031172040012,
"count": 222926,
"self": 310.8031172040012
}
}
},
"workers": {
"total": 3.6043563959829044,
"count": 231917,
"self": 0.0,
"children": {
"worker_root": {
"total": 2713.9470599229676,
"count": 231917,
"is_parallel": true,
"self": 1270.8950262360036,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001124432000096931,
"count": 1,
"is_parallel": true,
"self": 0.0003352179999183136,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007892140001786174,
"count": 2,
"is_parallel": true,
"self": 0.0007892140001786174
}
}
},
"UnityEnvironment.step": {
"total": 0.029618680999874414,
"count": 1,
"is_parallel": true,
"self": 0.0003561030000582832,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023494099991694384,
"count": 1,
"is_parallel": true,
"self": 0.00023494099991694384
},
"communicator.exchange": {
"total": 0.028271152999877813,
"count": 1,
"is_parallel": true,
"self": 0.028271152999877813
},
"steps_from_proto": {
"total": 0.0007564840000213735,
"count": 1,
"is_parallel": true,
"self": 0.00020564100009323738,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005508429999281361,
"count": 2,
"is_parallel": true,
"self": 0.0005508429999281361
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1443.052033686964,
"count": 231916,
"is_parallel": true,
"self": 43.590768730037325,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.27661074091634,
"count": 231916,
"is_parallel": true,
"self": 84.27661074091634
},
"communicator.exchange": {
"total": 1206.622553191012,
"count": 231916,
"is_parallel": true,
"self": 1206.622553191012
},
"steps_from_proto": {
"total": 108.56210102499836,
"count": 231916,
"is_parallel": true,
"self": 37.42711044293742,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.13499058206094,
"count": 463832,
"is_parallel": true,
"self": 71.13499058206094
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 600.1318466780697,
"count": 231917,
"self": 8.39345451408667,
"children": {
"process_trajectory": {
"total": 146.1552272189847,
"count": 231917,
"self": 144.56226433998472,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5929628789999697,
"count": 10,
"self": 1.5929628789999697
}
}
},
"_update_policy": {
"total": 445.5831649449983,
"count": 96,
"self": 381.1498487009949,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.43331624400344,
"count": 2880,
"self": 64.43331624400344
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6580002011323813e-06,
"count": 1,
"self": 1.6580002011323813e-06
},
"TrainerController._save_models": {
"total": 0.19625260499969954,
"count": 1,
"self": 0.0029117809999661404,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1933408239997334,
"count": 1,
"self": 0.1933408239997334
}
}
}
}
}
}
}