ppo-pyramids / run_logs /timers.json
qwerder's picture
First Push
9db4140 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.7267240285873413,
"min": 0.7267240285873413,
"max": 1.474189043045044,
"count": 16
},
"Pyramids.Policy.Entropy.sum": {
"value": 21883.11328125,
"min": 21883.11328125,
"max": 44721.0,
"count": 16
},
"Pyramids.Step.mean": {
"value": 479953.0,
"min": 29952.0,
"max": 479953.0,
"count": 16
},
"Pyramids.Step.sum": {
"value": 479953.0,
"min": 29952.0,
"max": 479953.0,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.05541457235813141,
"min": -0.0933021828532219,
"max": 0.06186692416667938,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -13.465741157531738,
"min": -22.29922103881836,
"max": 14.662461280822754,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02651437558233738,
"min": 0.02651437558233738,
"max": 0.31631937623023987,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.4429931640625,
"min": 6.4429931640625,
"max": 75.9166488647461,
"count": 16
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06906288433789574,
"min": 0.06626797814656406,
"max": 0.07218327643561119,
"count": 16
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0359432650684361,
"min": 0.46387584702594836,
"max": 1.0359432650684361,
"count": 16
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0020840348605572242,
"min": 0.0006468428421940135,
"max": 0.006202781256627953,
"count": 16
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.03126052290835837,
"min": 0.00905579979071619,
"max": 0.04362235728794806,
"count": 16
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.0953771108084453e-05,
"min": 2.0953771108084453e-05,
"max": 0.00029030127977321184,
"count": 16
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0003143065666212668,
"min": 0.0003143065666212668,
"max": 0.0030866082979146034,
"count": 16
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10698455936421464,
"min": 0.10698455936421464,
"max": 0.19676709218010133,
"count": 16
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.6047683904632195,
"min": 1.3382273235453528,
"max": 2.338651122697755,
"count": 16
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0007077574804850391,
"min": 0.0007077574804850391,
"max": 0.009677032508792125,
"count": 16
},
"Pyramids.Policy.Beta.sum": {
"value": 0.010616362207275586,
"min": 0.010616362207275586,
"max": 0.10291404729190542,
"count": 16
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.02306647039949894,
"min": 0.02306647039949894,
"max": 0.4807880222797394,
"count": 16
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.34599706530570984,
"min": 0.34599706530570984,
"max": 3.365516185760498,
"count": 16
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 948.4193548387096,
"min": 920.3333333333334,
"max": 999.0,
"count": 16
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29401.0,
"min": 15984.0,
"max": 33091.0,
"count": 16
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.6264258594282212,
"min": -1.0000000521540642,
"max": -0.5736063027288765,
"count": 16
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -19.419201642274857,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.6264258594282212,
"min": -1.0000000521540642,
"max": -0.5736063027288765,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -19.419201642274857,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 16
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.23303334911413973,
"min": 0.23303334911413973,
"max": 10.063545487821102,
"count": 16
},
"Pyramids.Policy.RndReward.sum": {
"value": 7.224033822538331,
"min": 7.224033822538331,
"max": 161.01672780513763,
"count": 16
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1764102598",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1764103576"
},
"total": 978.298390941,
"count": 1,
"self": 0.5294242939999094,
"children": {
"run_training.setup": {
"total": 0.02319117299998652,
"count": 1,
"self": 0.02319117299998652
},
"TrainerController.start_learning": {
"total": 977.7457754740001,
"count": 1,
"self": 0.5860807000008208,
"children": {
"TrainerController._reset_env": {
"total": 2.0403509029999896,
"count": 1,
"self": 2.0403509029999896
},
"TrainerController.advance": {
"total": 975.0486032809995,
"count": 31572,
"self": 0.6118296800093503,
"children": {
"env_step": {
"total": 659.8090884870157,
"count": 31572,
"self": 590.8466374029981,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.59875207003233,
"count": 31572,
"self": 2.125923307047742,
"children": {
"TorchPolicy.evaluate": {
"total": 66.47282876298459,
"count": 31321,
"self": 66.47282876298459
}
}
},
"workers": {
"total": 0.3636990139852969,
"count": 31572,
"self": 0.0,
"children": {
"worker_root": {
"total": 974.572076264981,
"count": 31572,
"is_parallel": true,
"self": 437.6532301949924,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019135119998736627,
"count": 1,
"is_parallel": true,
"self": 0.0006599150001420639,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012535969997315988,
"count": 8,
"is_parallel": true,
"self": 0.0012535969997315988
}
}
},
"UnityEnvironment.step": {
"total": 0.04865638499995839,
"count": 1,
"is_parallel": true,
"self": 0.0005309859996032174,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047192100009851856,
"count": 1,
"is_parallel": true,
"self": 0.00047192100009851856
},
"communicator.exchange": {
"total": 0.04605909700012489,
"count": 1,
"is_parallel": true,
"self": 0.04605909700012489
},
"steps_from_proto": {
"total": 0.0015943810001317615,
"count": 1,
"is_parallel": true,
"self": 0.0003685500000756292,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012258310000561323,
"count": 8,
"is_parallel": true,
"self": 0.0012258310000561323
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 536.9188460699886,
"count": 31571,
"is_parallel": true,
"self": 16.040969970953256,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 10.989017186979481,
"count": 31571,
"is_parallel": true,
"self": 10.989017186979481
},
"communicator.exchange": {
"total": 459.5352215930345,
"count": 31571,
"is_parallel": true,
"self": 459.5352215930345
},
"steps_from_proto": {
"total": 50.353637319021345,
"count": 31571,
"is_parallel": true,
"self": 10.41507463697235,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.938562682048996,
"count": 252568,
"is_parallel": true,
"self": 39.938562682048996
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 314.6276851139744,
"count": 31572,
"self": 1.0614962550080236,
"children": {
"process_trajectory": {
"total": 56.99470850896296,
"count": 31572,
"self": 56.889235525962704,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10547298300025432,
"count": 1,
"self": 0.10547298300025432
}
}
},
"_update_policy": {
"total": 256.5714803500034,
"count": 212,
"self": 144.62193908703648,
"children": {
"TorchPPOOptimizer.update": {
"total": 111.94954126296693,
"count": 11424,
"self": 111.94954126296693
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.199999683711212e-07,
"count": 1,
"self": 8.199999683711212e-07
},
"TrainerController._save_models": {
"total": 0.07073976999981824,
"count": 1,
"self": 0.0010010569999394647,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06973871299987877,
"count": 1,
"self": 0.06973871299987877
}
}
}
}
}
}
}