ppo-Huggy / run_logs /timers.json
JoeBater's picture
Huggy
27362c4 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408288836479187,
"min": 1.408288836479187,
"max": 1.4302749633789062,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70422.890625,
"min": 68842.203125,
"max": 76419.140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 109.7292576419214,
"min": 77.34796238244515,
"max": 379.4436090225564,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50256.0,
"min": 48912.0,
"max": 50466.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999964.0,
"min": 49999.0,
"max": 1999964.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999964.0,
"min": 49999.0,
"max": 1999964.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3272688388824463,
"min": 0.11729918420314789,
"max": 2.455440044403076,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1065.88916015625,
"min": 15.483491897583008,
"max": 1518.4478759765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.519275087586657,
"min": 1.8272416975462076,
"max": 3.966575242815731,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1611.8279901146889,
"min": 241.1959040760994,
"max": 2452.113386452198,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.519275087586657,
"min": 1.8272416975462076,
"max": 3.966575242815731,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1611.8279901146889,
"min": 241.1959040760994,
"max": 2452.113386452198,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017375212930589138,
"min": 0.014060282291514644,
"max": 0.021413463850816092,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05212563879176741,
"min": 0.02812056458302929,
"max": 0.05972291008026029,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0461519850211011,
"min": 0.02170037863155206,
"max": 0.05903505496680737,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1384559550633033,
"min": 0.04340075726310412,
"max": 0.1669917929917574,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3645988784999924e-06,
"min": 3.3645988784999924e-06,
"max": 0.0002953335015554999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0093796635499978e-05,
"min": 1.0093796635499978e-05,
"max": 0.0008438986687004499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10112150000000002,
"min": 0.10112150000000002,
"max": 0.19844450000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30336450000000004,
"min": 0.20737069999999996,
"max": 0.58129955,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.596284999999989e-05,
"min": 6.596284999999989e-05,
"max": 0.004922380549999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019788854999999966,
"min": 0.00019788854999999966,
"max": 0.014066847545000004,
"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": "1724058045",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "1724060733"
},
"total": 2687.785048955,
"count": 1,
"self": 0.4904458920000252,
"children": {
"run_training.setup": {
"total": 0.061339914999962275,
"count": 1,
"self": 0.061339914999962275
},
"TrainerController.start_learning": {
"total": 2687.233263148,
"count": 1,
"self": 5.4305526400057715,
"children": {
"TrainerController._reset_env": {
"total": 2.7018383450000556,
"count": 1,
"self": 2.7018383450000556
},
"TrainerController.advance": {
"total": 2678.973804868994,
"count": 232546,
"self": 5.491300427884653,
"children": {
"env_step": {
"total": 2162.8859188260944,
"count": 232546,
"self": 1781.1058248152112,
"children": {
"SubprocessEnvManager._take_step": {
"total": 378.13813129698474,
"count": 232546,
"self": 19.002348193060698,
"children": {
"TorchPolicy.evaluate": {
"total": 359.13578310392404,
"count": 223118,
"self": 359.13578310392404
}
}
},
"workers": {
"total": 3.641962713898579,
"count": 232546,
"self": 0.0,
"children": {
"worker_root": {
"total": 2678.8516016429217,
"count": 232546,
"is_parallel": true,
"self": 1254.9033907669175,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012198770000395598,
"count": 1,
"is_parallel": true,
"self": 0.0003858659999878,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008340110000517598,
"count": 2,
"is_parallel": true,
"self": 0.0008340110000517598
}
}
},
"UnityEnvironment.step": {
"total": 0.03169327199998406,
"count": 1,
"is_parallel": true,
"self": 0.00042131000009248964,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002186709999705272,
"count": 1,
"is_parallel": true,
"self": 0.0002186709999705272
},
"communicator.exchange": {
"total": 0.030271145999904547,
"count": 1,
"is_parallel": true,
"self": 0.030271145999904547
},
"steps_from_proto": {
"total": 0.0007821450000164987,
"count": 1,
"is_parallel": true,
"self": 0.00020510900003500865,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00057703599998149,
"count": 2,
"is_parallel": true,
"self": 0.00057703599998149
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1423.9482108760042,
"count": 232545,
"is_parallel": true,
"self": 42.67532531077427,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.66867340000147,
"count": 232545,
"is_parallel": true,
"self": 90.66867340000147
},
"communicator.exchange": {
"total": 1189.4388151361181,
"count": 232545,
"is_parallel": true,
"self": 1189.4388151361181
},
"steps_from_proto": {
"total": 101.16539702911041,
"count": 232545,
"is_parallel": true,
"self": 37.61732315720053,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.54807387190988,
"count": 465090,
"is_parallel": true,
"self": 63.54807387190988
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 510.5965856150152,
"count": 232546,
"self": 8.545199936941572,
"children": {
"process_trajectory": {
"total": 174.9424437030715,
"count": 232546,
"self": 173.48478556607154,
"children": {
"RLTrainer._checkpoint": {
"total": 1.457658136999953,
"count": 10,
"self": 1.457658136999953
}
}
},
"_update_policy": {
"total": 327.10894197500215,
"count": 97,
"self": 262.95330137598944,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.15564059901271,
"count": 2910,
"self": 64.15564059901271
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.13000349100912e-07,
"count": 1,
"self": 9.13000349100912e-07
},
"TrainerController._save_models": {
"total": 0.1270663809996222,
"count": 1,
"self": 0.0021611369993479457,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12490524400027425,
"count": 1,
"self": 0.12490524400027425
}
}
}
}
}
}
}