ppo-Pyramids / run_logs /timers.json
mxbonn's picture
First Push
120af0c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.28078493475914,
"min": 0.2677437663078308,
"max": 1.423993706703186,
"count": 50
},
"Pyramids.Policy.Entropy.sum": {
"value": 8414.5625,
"min": 8015.177734375,
"max": 43198.2734375,
"count": 50
},
"Pyramids.Step.mean": {
"value": 1499924.0,
"min": 29960.0,
"max": 1499924.0,
"count": 50
},
"Pyramids.Step.sum": {
"value": 1499924.0,
"min": 29960.0,
"max": 1499924.0,
"count": 50
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6669196486473083,
"min": -0.10112583637237549,
"max": 0.7618356943130493,
"count": 50
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 187.4044189453125,
"min": -24.371326446533203,
"max": 225.5033721923828,
"count": 50
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.006291675381362438,
"min": -0.01190947461873293,
"max": 0.23314324021339417,
"count": 50
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.767960786819458,
"min": -2.9773685932159424,
"max": 55.954376220703125,
"count": 50
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07099164538732211,
"min": 0.06582211494831079,
"max": 0.07398803724960674,
"count": 50
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0648746808098317,
"min": 0.5020745247977132,
"max": 1.0648746808098317,
"count": 50
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016909965320590737,
"min": 0.000580583540990847,
"max": 0.017521500551144733,
"count": 50
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.25364947980886104,
"min": 0.005225251868917623,
"max": 0.25364947980886104,
"count": 50
},
"Pyramids.Policy.LearningRate.mean": {
"value": 3.0265123245288865e-06,
"min": 3.0265123245288865e-06,
"max": 0.00029676708679192377,
"count": 50
},
"Pyramids.Policy.LearningRate.sum": {
"value": 4.53976848679333e-05,
"min": 4.53976848679333e-05,
"max": 0.0037382445539185325,
"count": 50
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10100880444444445,
"min": 0.10100880444444445,
"max": 0.19892236190476195,
"count": 50
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5151320666666668,
"min": 1.3924565333333336,
"max": 2.6460814666666668,
"count": 50
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00011077956399999993,
"min": 0.00011077956399999993,
"max": 0.009892343954285714,
"count": 50
},
"Pyramids.Policy.Beta.sum": {
"value": 0.001661693459999999,
"min": 0.001661693459999999,
"max": 0.12462353852000001,
"count": 50
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007417710963636637,
"min": 0.007369990926235914,
"max": 0.48865583539009094,
"count": 50
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11126566678285599,
"min": 0.10317987203598022,
"max": 3.420590877532959,
"count": 50
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 303.5050505050505,
"min": 247.07563025210084,
"max": 999.0,
"count": 50
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30047.0,
"min": 16759.0,
"max": 32750.0,
"count": 50
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.656080788885704,
"min": -0.9999871489501768,
"max": 1.7529243547625903,
"count": 50
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 163.95199809968472,
"min": -31.99920167028904,
"max": 208.59799821674824,
"count": 50
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.656080788885704,
"min": -0.9999871489501768,
"max": 1.7529243547625903,
"count": 50
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 163.95199809968472,
"min": -31.99920167028904,
"max": 208.59799821674824,
"count": 50
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.02325520820335386,
"min": 0.021491686257024547,
"max": 9.801928335033795,
"count": 50
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.3022656121320324,
"min": 2.283529032865772,
"max": 166.63278169557452,
"count": 50
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1677664200",
"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 --base-port 9999 --force",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.14.0a0+410ce96",
"numpy_version": "1.22.2",
"end_time_seconds": "1677668490"
},
"total": 4290.263005843386,
"count": 1,
"self": 0.5270892307162285,
"children": {
"run_training.setup": {
"total": 0.09279821626842022,
"count": 1,
"self": 0.09279821626842022
},
"TrainerController.start_learning": {
"total": 4289.643118396401,
"count": 1,
"self": 2.5794520247727633,
"children": {
"TrainerController._reset_env": {
"total": 2.5617526322603226,
"count": 1,
"self": 2.5617526322603226
},
"TrainerController.advance": {
"total": 4284.338959041983,
"count": 96494,
"self": 2.5303352009505033,
"children": {
"env_step": {
"total": 2781.8916279636323,
"count": 96494,
"self": 2611.498404601589,
"children": {
"SubprocessEnvManager._take_step": {
"total": 168.80392590165138,
"count": 96494,
"self": 7.274066103622317,
"children": {
"TorchPolicy.evaluate": {
"total": 161.52985979802907,
"count": 93808,
"self": 52.789940528571606,
"children": {
"TorchPolicy.sample_actions": {
"total": 108.73991926945746,
"count": 93808,
"self": 108.73991926945746
}
}
}
}
},
"workers": {
"total": 1.5892974603921175,
"count": 96494,
"self": 0.0,
"children": {
"worker_root": {
"total": 4283.924299772829,
"count": 96494,
"is_parallel": true,
"self": 1861.1004040073603,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004981350153684616,
"count": 1,
"is_parallel": true,
"self": 0.0014766249805688858,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0035047251731157303,
"count": 8,
"is_parallel": true,
"self": 0.0035047251731157303
}
}
},
"UnityEnvironment.step": {
"total": 0.055887987837195396,
"count": 1,
"is_parallel": true,
"self": 0.0005972646176815033,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005237050354480743,
"count": 1,
"is_parallel": true,
"self": 0.0005237050354480743
},
"communicator.exchange": {
"total": 0.05298143997788429,
"count": 1,
"is_parallel": true,
"self": 0.05298143997788429
},
"steps_from_proto": {
"total": 0.0017855782061815262,
"count": 1,
"is_parallel": true,
"self": 0.00045024603605270386,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013353321701288223,
"count": 8,
"is_parallel": true,
"self": 0.0013353321701288223
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2422.8238957654685,
"count": 96493,
"is_parallel": true,
"self": 63.50635749101639,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 45.96823373809457,
"count": 96493,
"is_parallel": true,
"self": 45.96823373809457
},
"communicator.exchange": {
"total": 2128.455231398344,
"count": 96493,
"is_parallel": true,
"self": 2128.455231398344
},
"steps_from_proto": {
"total": 184.89407313801348,
"count": 96493,
"is_parallel": true,
"self": 46.50435658544302,
"children": {
"_process_rank_one_or_two_observation": {
"total": 138.38971655257046,
"count": 771944,
"is_parallel": true,
"self": 138.38971655257046
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1499.9169958774,
"count": 96494,
"self": 4.972165144979954,
"children": {
"process_trajectory": {
"total": 259.17371026054025,
"count": 96494,
"self": 258.75394091010094,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4197693504393101,
"count": 3,
"self": 0.4197693504393101
}
}
},
"_update_policy": {
"total": 1235.7711204718798,
"count": 684,
"self": 404.66007146798074,
"children": {
"TorchPPOOptimizer.update": {
"total": 831.1110490038991,
"count": 34221,
"self": 831.1110490038991
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4659017324447632e-06,
"count": 1,
"self": 1.4659017324447632e-06
},
"TrainerController._save_models": {
"total": 0.1629532314836979,
"count": 1,
"self": 0.007886605337262154,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15506662614643574,
"count": 1,
"self": 0.15506662614643574
}
}
}
}
}
}
}