ppo-Huggy / run_logs /timers.json
DumbleDuck's picture
Huggy
23a6706 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4059373140335083,
"min": 1.4059373140335083,
"max": 1.4245742559432983,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71144.6484375,
"min": 68796.3046875,
"max": 78616.046875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.6594982078853,
"min": 79.3784665579119,
"max": 404.94354838709677,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49472.0,
"min": 48659.0,
"max": 50213.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999985.0,
"min": 49774.0,
"max": 1999985.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999985.0,
"min": 49774.0,
"max": 1999985.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.404966354370117,
"min": 0.029165517538785934,
"max": 2.441664457321167,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1341.97119140625,
"min": 3.5873587131500244,
"max": 1467.818603515625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6764417410324124,
"min": 1.7619104191539734,
"max": 3.962439571057352,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2051.454491496086,
"min": 216.71498155593872,
"max": 2356.135104715824,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6764417410324124,
"min": 1.7619104191539734,
"max": 3.962439571057352,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2051.454491496086,
"min": 216.71498155593872,
"max": 2356.135104715824,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01745244062767597,
"min": 0.013418951601003452,
"max": 0.019175715477225214,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.052357321883027906,
"min": 0.026837903202006904,
"max": 0.05631510256498586,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05469779790275627,
"min": 0.0253581488194565,
"max": 0.05965318336255021,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1640933937082688,
"min": 0.050716297638913,
"max": 0.17895955008765063,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.26429891193334e-06,
"min": 3.26429891193334e-06,
"max": 0.00029530507656497495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.79289673580002e-06,
"min": 9.79289673580002e-06,
"max": 0.0008441326686224499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108806666666666,
"min": 0.10108806666666666,
"max": 0.19843502500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032642,
"min": 0.20732295,
"max": 0.58137755,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.429452666666677e-05,
"min": 6.429452666666677e-05,
"max": 0.004921907747499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019288358000000031,
"min": 0.00019288358000000031,
"max": 0.014070739745000003,
"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": "1744938416",
"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": "1744940945"
},
"total": 2529.23525117,
"count": 1,
"self": 0.43625767699995777,
"children": {
"run_training.setup": {
"total": 0.023388325000041732,
"count": 1,
"self": 0.023388325000041732
},
"TrainerController.start_learning": {
"total": 2528.775605168,
"count": 1,
"self": 4.5660909410703425,
"children": {
"TrainerController._reset_env": {
"total": 2.9241276830000515,
"count": 1,
"self": 2.9241276830000515
},
"TrainerController.advance": {
"total": 2521.1767157759296,
"count": 232248,
"self": 4.7428875289178904,
"children": {
"env_step": {
"total": 2025.9686485258883,
"count": 232248,
"self": 1584.019162131941,
"children": {
"SubprocessEnvManager._take_step": {
"total": 439.071027919,
"count": 232248,
"self": 16.327126112079213,
"children": {
"TorchPolicy.evaluate": {
"total": 422.7439018069208,
"count": 222996,
"self": 422.7439018069208
}
}
},
"workers": {
"total": 2.878458474947365,
"count": 232248,
"self": 0.0,
"children": {
"worker_root": {
"total": 2521.05843990601,
"count": 232248,
"is_parallel": true,
"self": 1233.4613225190542,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010880069999075204,
"count": 1,
"is_parallel": true,
"self": 0.000254607999977452,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008333989999300684,
"count": 2,
"is_parallel": true,
"self": 0.0008333989999300684
}
}
},
"UnityEnvironment.step": {
"total": 0.030313295000041762,
"count": 1,
"is_parallel": true,
"self": 0.00033954799982893746,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021762100004707463,
"count": 1,
"is_parallel": true,
"self": 0.00021762100004707463
},
"communicator.exchange": {
"total": 0.02899061800007985,
"count": 1,
"is_parallel": true,
"self": 0.02899061800007985
},
"steps_from_proto": {
"total": 0.0007655080000859016,
"count": 1,
"is_parallel": true,
"self": 0.0001890790001652931,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005764289999206085,
"count": 2,
"is_parallel": true,
"self": 0.0005764289999206085
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1287.5971173869557,
"count": 232247,
"is_parallel": true,
"self": 38.00873103568529,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.00974013316386,
"count": 232247,
"is_parallel": true,
"self": 84.00974013316386
},
"communicator.exchange": {
"total": 1075.8268104160913,
"count": 232247,
"is_parallel": true,
"self": 1075.8268104160913
},
"steps_from_proto": {
"total": 89.7518358020152,
"count": 232247,
"is_parallel": true,
"self": 33.047668058900854,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.70416774311434,
"count": 464494,
"is_parallel": true,
"self": 56.70416774311434
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 490.4651797211236,
"count": 232248,
"self": 7.0282739380916155,
"children": {
"process_trajectory": {
"total": 171.71781528103497,
"count": 232248,
"self": 170.45750537503568,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2603099059992928,
"count": 10,
"self": 1.2603099059992928
}
}
},
"_update_policy": {
"total": 311.719090501997,
"count": 97,
"self": 246.22548104000566,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.49360946199135,
"count": 2910,
"self": 65.49360946199135
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0510002539376728e-06,
"count": 1,
"self": 1.0510002539376728e-06
},
"TrainerController._save_models": {
"total": 0.10866971699988426,
"count": 1,
"self": 0.0016589309998380486,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10701078600004621,
"count": 1,
"self": 0.10701078600004621
}
}
}
}
}
}
}