ppo-Huggy / run_logs /timers.json
root-jlee's picture
Huggy
2cbb0a2 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3772810697555542,
"min": 1.3772810697555542,
"max": 1.4212868213653564,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68382.0078125,
"min": 67767.3515625,
"max": 78012.734375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 111.99548532731377,
"min": 84.01712328767124,
"max": 404.2983870967742,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49614.0,
"min": 48778.0,
"max": 50133.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999994.0,
"min": 49798.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999994.0,
"min": 49798.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.330538272857666,
"min": 0.09568528085947037,
"max": 2.4487180709838867,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1032.428466796875,
"min": 11.76928997039795,
"max": 1395.8138427734375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5808424735715105,
"min": 1.8867623844767005,
"max": 3.970450144093316,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1586.313215792179,
"min": 232.07177329063416,
"max": 2227.2625920772552,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5808424735715105,
"min": 1.8867623844767005,
"max": 3.970450144093316,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1586.313215792179,
"min": 232.07177329063416,
"max": 2227.2625920772552,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016858913507167016,
"min": 0.012876593195445214,
"max": 0.02092003874737808,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03371782701433403,
"min": 0.02575318639089043,
"max": 0.058548695597467795,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.03817125704760353,
"min": 0.021614124719053506,
"max": 0.04434429941078027,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.07634251409520706,
"min": 0.04322824943810701,
"max": 0.13265723567456006,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.477523507524995e-06,
"min": 4.477523507524995e-06,
"max": 0.00029531062656312497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.95504701504999e-06,
"min": 8.95504701504999e-06,
"max": 0.00084413536862155,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101492475,
"min": 0.101492475,
"max": 0.198436875,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20298495,
"min": 0.20298495,
"max": 0.58137845,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.447450249999996e-05,
"min": 8.447450249999996e-05,
"max": 0.0049220000625,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016894900499999992,
"min": 0.00016894900499999992,
"max": 0.014070784654999998,
"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": "1745212444",
"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": "1745215099"
},
"total": 2654.4446434839997,
"count": 1,
"self": 0.7949468539995905,
"children": {
"run_training.setup": {
"total": 0.02141139299999395,
"count": 1,
"self": 0.02141139299999395
},
"TrainerController.start_learning": {
"total": 2653.628285237,
"count": 1,
"self": 4.703579768985037,
"children": {
"TrainerController._reset_env": {
"total": 2.7376091799999926,
"count": 1,
"self": 2.7376091799999926
},
"TrainerController.advance": {
"total": 2645.4144648460147,
"count": 231749,
"self": 4.714837625906057,
"children": {
"env_step": {
"total": 2062.758979906034,
"count": 231749,
"self": 1582.5012388780096,
"children": {
"SubprocessEnvManager._take_step": {
"total": 477.40838395198676,
"count": 231749,
"self": 16.224262144894453,
"children": {
"TorchPolicy.evaluate": {
"total": 461.1841218070923,
"count": 223051,
"self": 461.1841218070923
}
}
},
"workers": {
"total": 2.849357076037279,
"count": 231749,
"self": 0.0,
"children": {
"worker_root": {
"total": 2645.007801100063,
"count": 231749,
"is_parallel": true,
"self": 1357.0041868020544,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010222399999975096,
"count": 1,
"is_parallel": true,
"self": 0.00037563699999054734,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006466030000069622,
"count": 2,
"is_parallel": true,
"self": 0.0006466030000069622
}
}
},
"UnityEnvironment.step": {
"total": 0.03697689200004106,
"count": 1,
"is_parallel": true,
"self": 0.0003182850000484905,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018731599999455284,
"count": 1,
"is_parallel": true,
"self": 0.00018731599999455284
},
"communicator.exchange": {
"total": 0.03578314399999272,
"count": 1,
"is_parallel": true,
"self": 0.03578314399999272
},
"steps_from_proto": {
"total": 0.0006881470000053014,
"count": 1,
"is_parallel": true,
"self": 0.00019805300001962678,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004900939999856746,
"count": 2,
"is_parallel": true,
"self": 0.0004900939999856746
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1288.0036142980084,
"count": 231748,
"is_parallel": true,
"self": 38.9725208789182,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.07449488100724,
"count": 231748,
"is_parallel": true,
"self": 84.07449488100724
},
"communicator.exchange": {
"total": 1074.2596717260622,
"count": 231748,
"is_parallel": true,
"self": 1074.2596717260622
},
"steps_from_proto": {
"total": 90.69692681202093,
"count": 231748,
"is_parallel": true,
"self": 31.99074835819323,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.706178453827704,
"count": 463496,
"is_parallel": true,
"self": 58.706178453827704
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 577.9406473140746,
"count": 231749,
"self": 6.894293370147352,
"children": {
"process_trajectory": {
"total": 178.9723559099288,
"count": 231749,
"self": 173.103854414929,
"children": {
"RLTrainer._checkpoint": {
"total": 5.868501494999805,
"count": 10,
"self": 5.868501494999805
}
}
},
"_update_policy": {
"total": 392.07399803399835,
"count": 96,
"self": 258.18721422299967,
"children": {
"TorchPPOOptimizer.update": {
"total": 133.88678381099868,
"count": 2880,
"self": 133.88678381099868
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3220001164881978e-06,
"count": 1,
"self": 1.3220001164881978e-06
},
"TrainerController._save_models": {
"total": 0.7726301200000307,
"count": 1,
"self": 0.02301080600000205,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7496193140000287,
"count": 1,
"self": 0.7496193140000287
}
}
}
}
}
}
}