ppo-Huggy / run_logs /timers.json
AGI-CEO's picture
Huggy
ea8e2d5 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4019943475723267,
"min": 1.4019932746887207,
"max": 1.427046775817871,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68675.2890625,
"min": 68437.4921875,
"max": 75537.7421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 91.53631284916202,
"min": 81.83278145695364,
"max": 386.37692307692305,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49155.0,
"min": 49155.0,
"max": 50229.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999921.0,
"min": 49863.0,
"max": 1999921.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999921.0,
"min": 49863.0,
"max": 1999921.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4083218574523926,
"min": 0.14698319137096405,
"max": 2.48219895362854,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1290.8604736328125,
"min": 18.960832595825195,
"max": 1480.4432373046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6566877266141904,
"min": 1.7985567937987719,
"max": 3.9693048111554505,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1959.9846214652061,
"min": 232.01382640004158,
"max": 2302.064777493477,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6566877266141904,
"min": 1.7985567937987719,
"max": 3.9693048111554505,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1959.9846214652061,
"min": 232.01382640004158,
"max": 2302.064777493477,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015566941735960427,
"min": 0.013699945895738589,
"max": 0.02353839585036136,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04670082520788128,
"min": 0.027399891791477178,
"max": 0.05748170524440563,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054399763378832074,
"min": 0.023092215549614697,
"max": 0.05944854374974966,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16319929013649623,
"min": 0.04779659739385048,
"max": 0.17648560566206772,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.776398741233343e-06,
"min": 3.776398741233343e-06,
"max": 0.0002953281015573,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.132919622370003e-05,
"min": 1.132919622370003e-05,
"max": 0.0008440998186333998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125876666666671,
"min": 0.10125876666666671,
"max": 0.19844270000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037763000000001,
"min": 0.20766190000000007,
"max": 0.5813666,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.281245666666685e-05,
"min": 7.281245666666685e-05,
"max": 0.004922290730000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021843737000000056,
"min": 0.00021843737000000056,
"max": 0.01407019334,
"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": "1712833175",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1712835757"
},
"total": 2581.563712513,
"count": 1,
"self": 0.443972092000422,
"children": {
"run_training.setup": {
"total": 0.05913814200005163,
"count": 1,
"self": 0.05913814200005163
},
"TrainerController.start_learning": {
"total": 2581.060602279,
"count": 1,
"self": 4.599832855940349,
"children": {
"TrainerController._reset_env": {
"total": 2.8863075399999616,
"count": 1,
"self": 2.8863075399999616
},
"TrainerController.advance": {
"total": 2573.4564541980594,
"count": 232611,
"self": 5.044120379164269,
"children": {
"env_step": {
"total": 2081.7724323929556,
"count": 232611,
"self": 1724.1547251819475,
"children": {
"SubprocessEnvManager._take_step": {
"total": 354.38625973597027,
"count": 232611,
"self": 18.438470237899423,
"children": {
"TorchPolicy.evaluate": {
"total": 335.94778949807085,
"count": 222970,
"self": 335.94778949807085
}
}
},
"workers": {
"total": 3.231447475037726,
"count": 232611,
"self": 0.0,
"children": {
"worker_root": {
"total": 2573.1945234650143,
"count": 232611,
"is_parallel": true,
"self": 1183.4761668140145,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009868229999483447,
"count": 1,
"is_parallel": true,
"self": 0.00028980399986267,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006970190000856746,
"count": 2,
"is_parallel": true,
"self": 0.0006970190000856746
}
}
},
"UnityEnvironment.step": {
"total": 0.05639624900004492,
"count": 1,
"is_parallel": true,
"self": 0.00043295200009652035,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021821099994667748,
"count": 1,
"is_parallel": true,
"self": 0.00021821099994667748
},
"communicator.exchange": {
"total": 0.05485749499996473,
"count": 1,
"is_parallel": true,
"self": 0.05485749499996473
},
"steps_from_proto": {
"total": 0.0008875910000369913,
"count": 1,
"is_parallel": true,
"self": 0.0002542500001254666,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006333409999115247,
"count": 2,
"is_parallel": true,
"self": 0.0006333409999115247
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1389.7183566509998,
"count": 232610,
"is_parallel": true,
"self": 41.81141842795614,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.57523712402042,
"count": 232610,
"is_parallel": true,
"self": 92.57523712402042
},
"communicator.exchange": {
"total": 1156.1134753690021,
"count": 232610,
"is_parallel": true,
"self": 1156.1134753690021
},
"steps_from_proto": {
"total": 99.218225730021,
"count": 232610,
"is_parallel": true,
"self": 37.64362728915523,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.57459844086577,
"count": 465220,
"is_parallel": true,
"self": 61.57459844086577
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 486.63990142593957,
"count": 232611,
"self": 6.930632448960637,
"children": {
"process_trajectory": {
"total": 168.55940585897838,
"count": 232611,
"self": 167.04099790897817,
"children": {
"RLTrainer._checkpoint": {
"total": 1.51840795000021,
"count": 10,
"self": 1.51840795000021
}
}
},
"_update_policy": {
"total": 311.14986311800055,
"count": 97,
"self": 248.62974305998887,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.520120058011685,
"count": 2910,
"self": 62.520120058011685
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.82000074145617e-07,
"count": 1,
"self": 9.82000074145617e-07
},
"TrainerController._save_models": {
"total": 0.11800670299999183,
"count": 1,
"self": 0.0033050600000024133,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11470164299998942,
"count": 1,
"self": 0.11470164299998942
}
}
}
}
}
}
}