ppo-Huggy / run_logs /timers.json
HuggingDLRL's picture
My first Huggy
4749d93 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4042025804519653,
"min": 1.4042025804519653,
"max": 1.4238991737365723,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68909.8359375,
"min": 67953.375,
"max": 76992.2890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.7609561752988,
"min": 87.7854609929078,
"max": 408.9268292682927,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49578.0,
"min": 49237.0,
"max": 50298.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999999.0,
"min": 49671.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999999.0,
"min": 49671.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4462716579437256,
"min": -0.03297000005841255,
"max": 2.4462716579437256,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1228.0283203125,
"min": -4.022339820861816,
"max": 1361.197265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7670971533929207,
"min": 1.766022377815403,
"max": 3.9422237703929075,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1891.0827710032463,
"min": 215.45473009347916,
"max": 2138.473954975605,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7670971533929207,
"min": 1.766022377815403,
"max": 3.9422237703929075,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1891.0827710032463,
"min": 215.45473009347916,
"max": 2138.473954975605,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019185418345215213,
"min": 0.014379685700340714,
"max": 0.019185418345215213,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05755625503564564,
"min": 0.02903297016794871,
"max": 0.05755625503564564,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04745313732160462,
"min": 0.023506738152354954,
"max": 0.06342613564597235,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14235941196481386,
"min": 0.04701347630470991,
"max": 0.19027840693791706,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2477989174333305e-06,
"min": 3.2477989174333305e-06,
"max": 0.000295299826566725,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.743396752299991e-06,
"min": 9.743396752299991e-06,
"max": 0.0008440554186481999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108256666666667,
"min": 0.10108256666666667,
"max": 0.19843327500000008,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032477,
"min": 0.20732364999999994,
"max": 0.5813518,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.402007666666664e-05,
"min": 6.402007666666664e-05,
"max": 0.004921820422500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019206022999999992,
"min": 0.00019206022999999992,
"max": 0.014069454820000004,
"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": "1741571289",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741573636"
},
"total": 2347.524481503,
"count": 1,
"self": 0.4377914540000347,
"children": {
"run_training.setup": {
"total": 0.023296241000025475,
"count": 1,
"self": 0.023296241000025475
},
"TrainerController.start_learning": {
"total": 2347.063393808,
"count": 1,
"self": 4.0649593849598205,
"children": {
"TrainerController._reset_env": {
"total": 3.2428911679999146,
"count": 1,
"self": 3.2428911679999146
},
"TrainerController.advance": {
"total": 2339.64274772104,
"count": 231963,
"self": 4.23695572186989,
"children": {
"env_step": {
"total": 1848.5832450050577,
"count": 231963,
"self": 1444.5211346432338,
"children": {
"SubprocessEnvManager._take_step": {
"total": 401.6023742977907,
"count": 231963,
"self": 14.895912177600849,
"children": {
"TorchPolicy.evaluate": {
"total": 386.7064621201898,
"count": 222952,
"self": 386.7064621201898
}
}
},
"workers": {
"total": 2.4597360640332226,
"count": 231963,
"self": 0.0,
"children": {
"worker_root": {
"total": 2340.105130686941,
"count": 231963,
"is_parallel": true,
"self": 1157.3367995509211,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0013067209999917395,
"count": 1,
"is_parallel": true,
"self": 0.0004996739996840915,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000807047000307648,
"count": 2,
"is_parallel": true,
"self": 0.000807047000307648
}
}
},
"UnityEnvironment.step": {
"total": 0.02934130600010576,
"count": 1,
"is_parallel": true,
"self": 0.00033003999988068244,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018762800004878954,
"count": 1,
"is_parallel": true,
"self": 0.00018762800004878954
},
"communicator.exchange": {
"total": 0.028128369000114617,
"count": 1,
"is_parallel": true,
"self": 0.028128369000114617
},
"steps_from_proto": {
"total": 0.0006952690000616712,
"count": 1,
"is_parallel": true,
"self": 0.00019063899981119903,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005046300002504722,
"count": 2,
"is_parallel": true,
"self": 0.0005046300002504722
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1182.7683311360197,
"count": 231962,
"is_parallel": true,
"self": 36.22581055583464,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.14381368104705,
"count": 231962,
"is_parallel": true,
"self": 78.14381368104705
},
"communicator.exchange": {
"total": 985.210226224108,
"count": 231962,
"is_parallel": true,
"self": 985.210226224108
},
"steps_from_proto": {
"total": 83.18848067502995,
"count": 231962,
"is_parallel": true,
"self": 29.071278792097473,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.11720188293248,
"count": 463924,
"is_parallel": true,
"self": 54.11720188293248
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 486.82254699411214,
"count": 231963,
"self": 5.887622962012983,
"children": {
"process_trajectory": {
"total": 148.85558436409997,
"count": 231963,
"self": 147.5330661941009,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3225181699990571,
"count": 10,
"self": 1.3225181699990571
}
}
},
"_update_policy": {
"total": 332.0793396679992,
"count": 97,
"self": 265.3578789239966,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.72146074400257,
"count": 2910,
"self": 66.72146074400257
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.180002962239087e-07,
"count": 1,
"self": 9.180002962239087e-07
},
"TrainerController._save_models": {
"total": 0.11279461599997376,
"count": 1,
"self": 0.001831778999985545,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11096283699998821,
"count": 1,
"self": 0.11096283699998821
}
}
}
}
}
}
}