ppo-Huggy / run_logs /timers.json
Kidjon's picture
Huggy
9319f49 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4020112752914429,
"min": 1.4020112752914429,
"max": 1.4261995553970337,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70704.828125,
"min": 68069.7734375,
"max": 76855.34375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 95.72727272727273,
"min": 86.96660808435853,
"max": 385.2923076923077,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49491.0,
"min": 49168.0,
"max": 50088.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999891.0,
"min": 49735.0,
"max": 1999891.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999891.0,
"min": 49735.0,
"max": 1999891.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.441721200942993,
"min": 0.120570607483387,
"max": 2.458004951477051,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1262.369873046875,
"min": 15.553607940673828,
"max": 1363.0743408203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.760681702159129,
"min": 1.9912103296712387,
"max": 3.9466796249401668,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1944.2724400162697,
"min": 256.8661325275898,
"max": 2184.701847612858,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.760681702159129,
"min": 1.9912103296712387,
"max": 3.9466796249401668,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1944.2724400162697,
"min": 256.8661325275898,
"max": 2184.701847612858,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01836546278177088,
"min": 0.013211782233641618,
"max": 0.019801352087718743,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.055096388345312636,
"min": 0.026423564467283236,
"max": 0.055096388345312636,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05129418360690275,
"min": 0.021000201410303513,
"max": 0.06004067944983641,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15388255082070826,
"min": 0.042000402820607026,
"max": 0.1696335991223653,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.24399891870001e-06,
"min": 3.24399891870001e-06,
"max": 0.00029527335157555,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.73199675610003e-06,
"min": 9.73199675610003e-06,
"max": 0.0008439099186967,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1010813,
"min": 0.1010813,
"max": 0.19842445000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032439,
"min": 0.20731545000000007,
"max": 0.5813033000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.395687000000019e-05,
"min": 6.395687000000019e-05,
"max": 0.004921380055,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001918706100000006,
"min": 0.0001918706100000006,
"max": 0.014067034669999999,
"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": "1721314570",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1721317407"
},
"total": 2836.641979449,
"count": 1,
"self": 0.44599267899911865,
"children": {
"run_training.setup": {
"total": 0.060973104000140665,
"count": 1,
"self": 0.060973104000140665
},
"TrainerController.start_learning": {
"total": 2836.1350136660003,
"count": 1,
"self": 5.602812807877399,
"children": {
"TrainerController._reset_env": {
"total": 3.073422505000053,
"count": 1,
"self": 3.073422505000053
},
"TrainerController.advance": {
"total": 2827.3320079801233,
"count": 232432,
"self": 5.74047709790193,
"children": {
"env_step": {
"total": 2285.0678492250863,
"count": 232432,
"self": 1881.6479821920336,
"children": {
"SubprocessEnvManager._take_step": {
"total": 399.6714793950043,
"count": 232432,
"self": 21.73057768797662,
"children": {
"TorchPolicy.evaluate": {
"total": 377.9409017070277,
"count": 223048,
"self": 377.9409017070277
}
}
},
"workers": {
"total": 3.7483876380483707,
"count": 232432,
"self": 0.0,
"children": {
"worker_root": {
"total": 2827.5403608209645,
"count": 232432,
"is_parallel": true,
"self": 1320.9017115049583,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009316859998307336,
"count": 1,
"is_parallel": true,
"self": 0.00025164799967569706,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006800380001550366,
"count": 2,
"is_parallel": true,
"self": 0.0006800380001550366
}
}
},
"UnityEnvironment.step": {
"total": 0.035443395000129385,
"count": 1,
"is_parallel": true,
"self": 0.00043878900009985955,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023193900005935575,
"count": 1,
"is_parallel": true,
"self": 0.00023193900005935575
},
"communicator.exchange": {
"total": 0.0338740530000905,
"count": 1,
"is_parallel": true,
"self": 0.0338740530000905
},
"steps_from_proto": {
"total": 0.0008986139998796716,
"count": 1,
"is_parallel": true,
"self": 0.00021960599974590878,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006790080001337628,
"count": 2,
"is_parallel": true,
"self": 0.0006790080001337628
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1506.6386493160062,
"count": 232431,
"is_parallel": true,
"self": 43.969533577796255,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 94.79316383411378,
"count": 232431,
"is_parallel": true,
"self": 94.79316383411378
},
"communicator.exchange": {
"total": 1263.3817075099776,
"count": 232431,
"is_parallel": true,
"self": 1263.3817075099776
},
"steps_from_proto": {
"total": 104.4942443941186,
"count": 232431,
"is_parallel": true,
"self": 39.57361600517402,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.92062838894458,
"count": 464862,
"is_parallel": true,
"self": 64.92062838894458
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 536.5236816571348,
"count": 232432,
"self": 8.631102981141566,
"children": {
"process_trajectory": {
"total": 183.9270653629926,
"count": 232432,
"self": 182.47528878699336,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4517765759992471,
"count": 10,
"self": 1.4517765759992471
}
}
},
"_update_policy": {
"total": 343.96551331300066,
"count": 97,
"self": 277.805055629002,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.16045768399863,
"count": 2910,
"self": 66.16045768399863
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0079997991851997e-06,
"count": 1,
"self": 1.0079997991851997e-06
},
"TrainerController._save_models": {
"total": 0.12676936499974545,
"count": 1,
"self": 0.0020594779998646118,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12470988699988084,
"count": 1,
"self": 0.12470988699988084
}
}
}
}
}
}
}