YoriV's picture
Pyramids first training
fbe67f4
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.24409466981887817,
"min": 0.23197020590305328,
"max": 1.4884732961654663,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 7221.296875,
"min": 6915.4267578125,
"max": 45154.32421875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989928.0,
"min": 29952.0,
"max": 989928.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989928.0,
"min": 29952.0,
"max": 989928.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6756728887557983,
"min": -0.20916101336479187,
"max": 0.7184569239616394,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 192.5667724609375,
"min": -49.57115936279297,
"max": 204.76022338867188,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.016984010115265846,
"min": -0.016984010115265846,
"max": 0.37566667795181274,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -4.840443134307861,
"min": -4.840443134307861,
"max": 89.03300476074219,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06901760601710218,
"min": 0.06531463671334288,
"max": 0.0734269839581213,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0352640902565327,
"min": 0.49526211200917586,
"max": 1.0704446528581215,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01796412523641872,
"min": 0.0006119087810834283,
"max": 0.01796412523641872,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2694618785462808,
"min": 0.005507179029750855,
"max": 0.2694618785462808,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.499337500253335e-06,
"min": 7.499337500253335e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011249006250380003,
"min": 0.00011249006250380003,
"max": 0.0035084642305119994,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249974666666667,
"min": 0.10249974666666667,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5374962,
"min": 1.3886848,
"max": 2.569488,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025972469200000013,
"min": 0.00025972469200000013,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003895870380000002,
"min": 0.003895870380000002,
"max": 0.1169718512,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011859537102282047,
"min": 0.011693320237100124,
"max": 0.4630510210990906,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17789305746555328,
"min": 0.1637064814567566,
"max": 3.2413570880889893,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 261.2962962962963,
"min": 261.188679245283,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28220.0,
"min": 15984.0,
"max": 33081.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7201796180948064,
"min": -1.0000000521540642,
"max": 1.7201796180948064,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 185.77939875423908,
"min": -31.999601677060127,
"max": 196.0801978185773,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7201796180948064,
"min": -1.0000000521540642,
"max": 1.7201796180948064,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 185.77939875423908,
"min": -31.999601677060127,
"max": 196.0801978185773,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03214376258822287,
"min": 0.03214376258822287,
"max": 9.698352985084057,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.4715263595280703,
"min": 3.4715263595280703,
"max": 155.1736477613449,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1676213423",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1676215843"
},
"total": 2419.8969255410007,
"count": 1,
"self": 0.42837118200077384,
"children": {
"run_training.setup": {
"total": 0.1080457939997359,
"count": 1,
"self": 0.1080457939997359
},
"TrainerController.start_learning": {
"total": 2419.360508565,
"count": 1,
"self": 1.4368376159541185,
"children": {
"TrainerController._reset_env": {
"total": 6.16713601299989,
"count": 1,
"self": 6.16713601299989
},
"TrainerController.advance": {
"total": 2411.6707913590467,
"count": 64251,
"self": 1.493548805040973,
"children": {
"env_step": {
"total": 1663.2245559830244,
"count": 64251,
"self": 1542.9957125740902,
"children": {
"SubprocessEnvManager._take_step": {
"total": 119.37426558196603,
"count": 64251,
"self": 4.776592154034461,
"children": {
"TorchPolicy.evaluate": {
"total": 114.59767342793157,
"count": 62560,
"self": 38.32300417096485,
"children": {
"TorchPolicy.sample_actions": {
"total": 76.27466925696672,
"count": 62560,
"self": 76.27466925696672
}
}
}
}
},
"workers": {
"total": 0.854577826968125,
"count": 64251,
"self": 0.0,
"children": {
"worker_root": {
"total": 2413.7140672240184,
"count": 64251,
"is_parallel": true,
"self": 991.0422653209962,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020020810002279177,
"count": 1,
"is_parallel": true,
"self": 0.0007851499995013,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012169310007266176,
"count": 8,
"is_parallel": true,
"self": 0.0012169310007266176
}
}
},
"UnityEnvironment.step": {
"total": 0.04737525900009132,
"count": 1,
"is_parallel": true,
"self": 0.0005789350002487481,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004807020000043849,
"count": 1,
"is_parallel": true,
"self": 0.0004807020000043849
},
"communicator.exchange": {
"total": 0.044532236000122793,
"count": 1,
"is_parallel": true,
"self": 0.044532236000122793
},
"steps_from_proto": {
"total": 0.0017833859997153922,
"count": 1,
"is_parallel": true,
"self": 0.0004533119999905466,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013300739997248456,
"count": 8,
"is_parallel": true,
"self": 0.0013300739997248456
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1422.6718019030222,
"count": 64250,
"is_parallel": true,
"self": 32.553867910132794,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.46276227383032,
"count": 64250,
"is_parallel": true,
"self": 24.46276227383032
},
"communicator.exchange": {
"total": 1257.511456893003,
"count": 64250,
"is_parallel": true,
"self": 1257.511456893003
},
"steps_from_proto": {
"total": 108.14371482605611,
"count": 64250,
"is_parallel": true,
"self": 24.284515957889198,
"children": {
"_process_rank_one_or_two_observation": {
"total": 83.85919886816691,
"count": 514000,
"is_parallel": true,
"self": 83.85919886816691
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 746.9526865709813,
"count": 64251,
"self": 2.73331136099614,
"children": {
"process_trajectory": {
"total": 171.0159312859837,
"count": 64251,
"self": 170.82486225798357,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19106902800012904,
"count": 2,
"self": 0.19106902800012904
}
}
},
"_update_policy": {
"total": 573.2034439240015,
"count": 448,
"self": 218.97983256600855,
"children": {
"TorchPPOOptimizer.update": {
"total": 354.2236113579929,
"count": 22791,
"self": 354.2236113579929
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.409995982423425e-07,
"count": 1,
"self": 9.409995982423425e-07
},
"TrainerController._save_models": {
"total": 0.08574263599984988,
"count": 1,
"self": 0.0019307040001876885,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08381193199966219,
"count": 1,
"self": 0.08381193199966219
}
}
}
}
}
}
}