ppo-Huggy / run_logs /timers.json
txia-m's picture
Huggy
ce830b9 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4020953178405762,
"min": 1.4020953178405762,
"max": 1.425697922706604,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68781.1875,
"min": 68156.8359375,
"max": 76085.40625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.45470085470086,
"min": 79.52665589660744,
"max": 411.10655737704917,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48821.0,
"min": 48708.0,
"max": 50203.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999963.0,
"min": 49566.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999963.0,
"min": 49566.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.442908763885498,
"min": 0.03271083906292915,
"max": 2.4901537895202637,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1429.1015625,
"min": 3.9580116271972656,
"max": 1496.455322265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.651386894018222,
"min": 1.8649587520390503,
"max": 3.9421518649125575,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2136.06133300066,
"min": 225.66000899672508,
"max": 2304.851822376251,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.651386894018222,
"min": 1.8649587520390503,
"max": 3.9421518649125575,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2136.06133300066,
"min": 225.66000899672508,
"max": 2304.851822376251,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016855817006176544,
"min": 0.012859419705637264,
"max": 0.02016160829480214,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050567451018529636,
"min": 0.02571883941127453,
"max": 0.05479855916977007,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056597017289863695,
"min": 0.022475454956293106,
"max": 0.06245227356751759,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1697910518695911,
"min": 0.04495090991258621,
"max": 0.18735682070255277,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4603488465833314e-06,
"min": 3.4603488465833314e-06,
"max": 0.00029535697654767496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0381046539749994e-05,
"min": 1.0381046539749994e-05,
"max": 0.0008440096686634501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115341666666666,
"min": 0.10115341666666666,
"max": 0.1984523250000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30346025,
"min": 0.20744735000000009,
"max": 0.58133655,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.755549166666664e-05,
"min": 6.755549166666664e-05,
"max": 0.004922771017499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020266647499999992,
"min": 0.00020266647499999992,
"max": 0.014068693845000002,
"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": "1767599302",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1767602009"
},
"total": 2707.815793717,
"count": 1,
"self": 0.4337230300002375,
"children": {
"run_training.setup": {
"total": 0.02525449099994148,
"count": 1,
"self": 0.02525449099994148
},
"TrainerController.start_learning": {
"total": 2707.3568161959997,
"count": 1,
"self": 4.484931234883334,
"children": {
"TrainerController._reset_env": {
"total": 3.3247394729999087,
"count": 1,
"self": 3.3247394729999087
},
"TrainerController.advance": {
"total": 2699.436268201117,
"count": 232595,
"self": 4.915997058219091,
"children": {
"env_step": {
"total": 2204.6042047779497,
"count": 232595,
"self": 1775.6015433560488,
"children": {
"SubprocessEnvManager._take_step": {
"total": 426.096820883942,
"count": 232595,
"self": 16.316701815894135,
"children": {
"TorchPolicy.evaluate": {
"total": 409.78011906804784,
"count": 222944,
"self": 409.78011906804784
}
}
},
"workers": {
"total": 2.905840537958852,
"count": 232595,
"self": 0.0,
"children": {
"worker_root": {
"total": 2694.2834179239676,
"count": 232595,
"is_parallel": true,
"self": 1260.4475082879258,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011641360000567147,
"count": 1,
"is_parallel": true,
"self": 0.00037358600013703835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007905499999196763,
"count": 2,
"is_parallel": true,
"self": 0.0007905499999196763
}
}
},
"UnityEnvironment.step": {
"total": 0.08378698900003201,
"count": 1,
"is_parallel": true,
"self": 0.000344972000107191,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001847300000008545,
"count": 1,
"is_parallel": true,
"self": 0.0001847300000008545
},
"communicator.exchange": {
"total": 0.08254659699991862,
"count": 1,
"is_parallel": true,
"self": 0.08254659699991862
},
"steps_from_proto": {
"total": 0.0007106900000053429,
"count": 1,
"is_parallel": true,
"self": 0.00017270199998620228,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005379880000191406,
"count": 2,
"is_parallel": true,
"self": 0.0005379880000191406
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1433.8359096360418,
"count": 232594,
"is_parallel": true,
"self": 40.511479001891985,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.50777353905426,
"count": 232594,
"is_parallel": true,
"self": 88.50777353905426
},
"communicator.exchange": {
"total": 1209.1355098750535,
"count": 232594,
"is_parallel": true,
"self": 1209.1355098750535
},
"steps_from_proto": {
"total": 95.68114722004191,
"count": 232594,
"is_parallel": true,
"self": 34.88394208385262,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.79720513618929,
"count": 465188,
"is_parallel": true,
"self": 60.79720513618929
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 489.91606636494816,
"count": 232595,
"self": 6.810632715000452,
"children": {
"process_trajectory": {
"total": 165.41807927894672,
"count": 232595,
"self": 164.20087561594698,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2172036629997365,
"count": 10,
"self": 1.2172036629997365
}
}
},
"_update_policy": {
"total": 317.687354371001,
"count": 97,
"self": 252.6690182100001,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.01833616100089,
"count": 2910,
"self": 65.01833616100089
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0069998097606003e-06,
"count": 1,
"self": 1.0069998097606003e-06
},
"TrainerController._save_models": {
"total": 0.11087627999995675,
"count": 1,
"self": 0.001552360999994562,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10932391899996219,
"count": 1,
"self": 0.10932391899996219
}
}
}
}
}
}
}