testpyramidsrnd / run_logs /timers.json
reza-aditya's picture
First Pyramids
ee8ef7b
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.8333196640014648,
"min": 0.8333196640014648,
"max": 1.5446901321411133,
"count": 16
},
"Pyramids.Policy.Entropy.sum": {
"value": 25426.25,
"min": 25426.25,
"max": 46859.71875,
"count": 16
},
"Pyramids.Step.mean": {
"value": 479892.0,
"min": 29951.0,
"max": 479892.0,
"count": 16
},
"Pyramids.Step.sum": {
"value": 479892.0,
"min": 29951.0,
"max": 479892.0,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.15133728086948395,
"min": -0.14972802996635437,
"max": 0.23076419532299042,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 38.136993408203125,
"min": -35.48554229736328,
"max": 59.306396484375,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.018685242161154747,
"min": -0.02655895985662937,
"max": 0.33884161710739136,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -4.708681106567383,
"min": -6.825652599334717,
"max": 80.30546569824219,
"count": 16
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06803610989369363,
"min": 0.06606335065133419,
"max": 0.07419561287504813,
"count": 16
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9525055385117108,
"min": 0.5193692901253368,
"max": 1.042200711206533,
"count": 16
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0114175668435824,
"min": 0.0004966965342846287,
"max": 0.012452507146095049,
"count": 16
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1598459358101536,
"min": 0.004966965342846287,
"max": 0.17433510004533068,
"count": 16
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.0986464433114283e-05,
"min": 2.0986464433114283e-05,
"max": 0.0002904659174637428,
"count": 16
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0002938105020636,
"min": 0.0002938105020636,
"max": 0.0030037650987449994,
"count": 16
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10699545714285714,
"min": 0.10699545714285714,
"max": 0.19682197142857147,
"count": 16
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4979364,
"min": 1.3777538000000003,
"max": 2.3395822,
"count": 16
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0007088461685714285,
"min": 0.0007088461685714285,
"max": 0.009682514945714284,
"count": 16
},
"Pyramids.Policy.Beta.sum": {
"value": 0.009923846359999999,
"min": 0.009923846359999999,
"max": 0.1001353745,
"count": 16
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.016978492960333824,
"min": 0.016717027872800827,
"max": 0.3108974099159241,
"count": 16
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.23769891262054443,
"min": 0.23403838276863098,
"max": 2.1762819290161133,
"count": 16
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 679.5555555555555,
"min": 628.4285714285714,
"max": 999.0,
"count": 16
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30580.0,
"min": 16622.0,
"max": 32415.0,
"count": 16
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.7425244053204855,
"min": -0.9999500517733395,
"max": 0.9224448590254297,
"count": 16
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 33.413598239421844,
"min": -31.998401656746864,
"max": 45.199798092246056,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.7425244053204855,
"min": -0.9999500517733395,
"max": 0.9224448590254297,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 33.413598239421844,
"min": -31.998401656746864,
"max": 45.199798092246056,
"count": 16
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.11839565777918323,
"min": 0.11172069520903372,
"max": 5.72171481216655,
"count": 16
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.327804600063246,
"min": 5.327804600063246,
"max": 97.26915180683136,
"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": "1668321305",
"python_version": "3.7.15 (default, Oct 12 2022, 19:14:55) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"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": "1668322543"
},
"total": 1238.397938718,
"count": 1,
"self": 0.4964497299999948,
"children": {
"run_training.setup": {
"total": 0.05236279700000068,
"count": 1,
"self": 0.05236279700000068
},
"TrainerController.start_learning": {
"total": 1237.8491261909999,
"count": 1,
"self": 0.9119359080029881,
"children": {
"TrainerController._reset_env": {
"total": 8.564547832000017,
"count": 1,
"self": 8.564547832000017
},
"TrainerController.advance": {
"total": 1228.2640401789968,
"count": 31710,
"self": 0.9877504019516437,
"children": {
"env_step": {
"total": 825.4304650860375,
"count": 31710,
"self": 757.9961539530303,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.9211016570066,
"count": 31710,
"self": 2.7823310330420554,
"children": {
"TorchPolicy.evaluate": {
"total": 64.13877062396455,
"count": 31324,
"self": 21.254137327966305,
"children": {
"TorchPolicy.sample_actions": {
"total": 42.88463329599824,
"count": 31324,
"self": 42.88463329599824
}
}
}
}
},
"workers": {
"total": 0.5132094760006112,
"count": 31710,
"self": 0.0,
"children": {
"worker_root": {
"total": 1235.0532119330117,
"count": 31710,
"is_parallel": true,
"self": 540.1949218020054,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005449626999961765,
"count": 1,
"is_parallel": true,
"self": 0.004028382000001329,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001421244999960436,
"count": 8,
"is_parallel": true,
"self": 0.001421244999960436
}
}
},
"UnityEnvironment.step": {
"total": 0.0542692359999819,
"count": 1,
"is_parallel": true,
"self": 0.0006251999999449254,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047575500002494664,
"count": 1,
"is_parallel": true,
"self": 0.00047575500002494664
},
"communicator.exchange": {
"total": 0.05132711900000686,
"count": 1,
"is_parallel": true,
"self": 0.05132711900000686
},
"steps_from_proto": {
"total": 0.0018411620000051698,
"count": 1,
"is_parallel": true,
"self": 0.0004899839999552569,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001351178000049913,
"count": 8,
"is_parallel": true,
"self": 0.001351178000049913
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 694.8582901310062,
"count": 31709,
"is_parallel": true,
"self": 16.663635032955995,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.51172909500724,
"count": 31709,
"is_parallel": true,
"self": 13.51172909500724
},
"communicator.exchange": {
"total": 604.4296983860214,
"count": 31709,
"is_parallel": true,
"self": 604.4296983860214
},
"steps_from_proto": {
"total": 60.253227617021594,
"count": 31709,
"is_parallel": true,
"self": 14.222217832971523,
"children": {
"_process_rank_one_or_two_observation": {
"total": 46.03100978405007,
"count": 253672,
"is_parallel": true,
"self": 46.03100978405007
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 401.8458246910076,
"count": 31710,
"self": 1.636247553995986,
"children": {
"process_trajectory": {
"total": 91.97607759301127,
"count": 31710,
"self": 91.86896855801115,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10710903500012137,
"count": 1,
"self": 0.10710903500012137
}
}
},
"_update_policy": {
"total": 308.2334995440003,
"count": 216,
"self": 121.51893671500659,
"children": {
"TorchPPOOptimizer.update": {
"total": 186.71456282899373,
"count": 11448,
"self": 186.71456282899373
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2620000688912114e-06,
"count": 1,
"self": 1.2620000688912114e-06
},
"TrainerController._save_models": {
"total": 0.10860101000002942,
"count": 1,
"self": 0.0019246169999860285,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10667639300004339,
"count": 1,
"self": 0.10667639300004339
}
}
}
}
}
}
}