ppo-Huggy / run_logs /timers.json
Slyne's picture
Huggy
ed626fa verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.401410698890686,
"min": 1.401410698890686,
"max": 1.4270752668380737,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68687.34375,
"min": 68687.34375,
"max": 76459.9609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.97368421052632,
"min": 87.82918149466192,
"max": 377.16541353383457,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49881.0,
"min": 49054.0,
"max": 50163.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999679.0,
"min": 49547.0,
"max": 1999679.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999679.0,
"min": 49547.0,
"max": 1999679.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3672962188720703,
"min": 0.17065703868865967,
"max": 2.425839900970459,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1169.4443359375,
"min": 22.526729583740234,
"max": 1352.4404296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6598509501831735,
"min": 1.8195822225375609,
"max": 3.9011724386580307,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1807.9663693904877,
"min": 240.18485337495804,
"max": 2100.167682826519,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6598509501831735,
"min": 1.8195822225375609,
"max": 3.9011724386580307,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1807.9663693904877,
"min": 240.18485337495804,
"max": 2100.167682826519,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015633066375448836,
"min": 0.014023401872772309,
"max": 0.01926801264976853,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.046899199126346505,
"min": 0.028338397437376747,
"max": 0.057804037949305595,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05620029763215118,
"min": 0.022009181727965673,
"max": 0.06431148544781738,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16860089289645355,
"min": 0.04441727542628844,
"max": 0.19293445634345213,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2316489228166595e-06,
"min": 3.2316489228166595e-06,
"max": 0.00029534220155259995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.694946768449979e-06,
"min": 9.694946768449979e-06,
"max": 0.0008440797186401,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10107718333333336,
"min": 0.10107718333333336,
"max": 0.1984474,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30323155000000007,
"min": 0.20736295,
"max": 0.5813598999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.375144833333323e-05,
"min": 6.375144833333323e-05,
"max": 0.004922525260000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001912543449999997,
"min": 0.0001912543449999997,
"max": 0.014069859009999998,
"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": "1739341323",
"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": "1739343780"
},
"total": 2457.254931788,
"count": 1,
"self": 0.4379600229999596,
"children": {
"run_training.setup": {
"total": 0.022918634999768983,
"count": 1,
"self": 0.022918634999768983
},
"TrainerController.start_learning": {
"total": 2456.79405313,
"count": 1,
"self": 4.434834706771653,
"children": {
"TrainerController._reset_env": {
"total": 3.459403548999944,
"count": 1,
"self": 3.459403548999944
},
"TrainerController.advance": {
"total": 2448.7803532442285,
"count": 231427,
"self": 4.43154410836587,
"children": {
"env_step": {
"total": 1969.5312974389403,
"count": 231427,
"self": 1542.6645378499247,
"children": {
"SubprocessEnvManager._take_step": {
"total": 424.2124571379595,
"count": 231427,
"self": 15.788554609891435,
"children": {
"TorchPolicy.evaluate": {
"total": 408.4239025280681,
"count": 222867,
"self": 408.4239025280681
}
}
},
"workers": {
"total": 2.6543024510560826,
"count": 231427,
"self": 0.0,
"children": {
"worker_root": {
"total": 2449.0008980389407,
"count": 231427,
"is_parallel": true,
"self": 1190.3294927619327,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012058990000696213,
"count": 1,
"is_parallel": true,
"self": 0.0004075580000062473,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007983410000633739,
"count": 2,
"is_parallel": true,
"self": 0.0007983410000633739
}
}
},
"UnityEnvironment.step": {
"total": 0.030361523999999918,
"count": 1,
"is_parallel": true,
"self": 0.00030730899970876635,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021301700007825275,
"count": 1,
"is_parallel": true,
"self": 0.00021301700007825275
},
"communicator.exchange": {
"total": 0.029129166000075202,
"count": 1,
"is_parallel": true,
"self": 0.029129166000075202
},
"steps_from_proto": {
"total": 0.0007120320001376967,
"count": 1,
"is_parallel": true,
"self": 0.00021018100005676388,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005018510000809329,
"count": 2,
"is_parallel": true,
"self": 0.0005018510000809329
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1258.671405277008,
"count": 231426,
"is_parallel": true,
"self": 37.091738613886264,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.22266575386811,
"count": 231426,
"is_parallel": true,
"self": 83.22266575386811
},
"communicator.exchange": {
"total": 1049.5550834331475,
"count": 231426,
"is_parallel": true,
"self": 1049.5550834331475
},
"steps_from_proto": {
"total": 88.80191747610615,
"count": 231426,
"is_parallel": true,
"self": 33.07989736037689,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.722020115729265,
"count": 462852,
"is_parallel": true,
"self": 55.722020115729265
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 474.81751169692234,
"count": 231427,
"self": 6.49638160309496,
"children": {
"process_trajectory": {
"total": 160.98489604682482,
"count": 231427,
"self": 159.4683316478231,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5165643990017088,
"count": 10,
"self": 1.5165643990017088
}
}
},
"_update_policy": {
"total": 307.33623404700256,
"count": 97,
"self": 243.535551827978,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.800682219024566,
"count": 2910,
"self": 63.800682219024566
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.380000847158954e-07,
"count": 1,
"self": 9.380000847158954e-07
},
"TrainerController._save_models": {
"total": 0.11946069199984777,
"count": 1,
"self": 0.0019057240006077336,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11755496799924003,
"count": 1,
"self": 0.11755496799924003
}
}
}
}
}
}
}