ppo-PyramidsRND / run_logs /timers.json
NathanaelM's picture
PyramidsRND initial training
b72cc3b
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2071920931339264,
"min": 0.201755091547966,
"max": 1.4341418743133545,
"count": 66
},
"Pyramids.Policy.Entropy.sum": {
"value": 6232.33837890625,
"min": 6030.05615234375,
"max": 43506.12890625,
"count": 66
},
"Pyramids.Step.mean": {
"value": 1979889.0,
"min": 29952.0,
"max": 1979889.0,
"count": 66
},
"Pyramids.Step.sum": {
"value": 1979889.0,
"min": 29952.0,
"max": 1979889.0,
"count": 66
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.8243393301963806,
"min": -0.09622462093830109,
"max": 0.9279937148094177,
"count": 66
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 248.9504852294922,
"min": -23.190134048461914,
"max": 290.4620361328125,
"count": 66
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.011662246659398079,
"min": -0.07439544796943665,
"max": 0.31239381432533264,
"count": 66
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.521998405456543,
"min": -21.42588996887207,
"max": 75.28691101074219,
"count": 66
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06858035875068577,
"min": 0.06510530802738725,
"max": 0.07328678109514018,
"count": 66
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9601250225096009,
"min": 0.5068921602656262,
"max": 1.0789347016446604,
"count": 66
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016518163341624176,
"min": 0.000323967105224438,
"max": 0.017910530448879643,
"count": 66
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23125428678273846,
"min": 0.002915703947019942,
"max": 0.250747426284315,
"count": 66
},
"Pyramids.Policy.LearningRate.mean": {
"value": 5.334291079078573e-06,
"min": 5.334291079078573e-06,
"max": 0.0002975753150939428,
"count": 66
},
"Pyramids.Policy.LearningRate.sum": {
"value": 7.468007510710002e-05,
"min": 7.468007510710002e-05,
"max": 0.0037903268865577496,
"count": 66
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1017780642857143,
"min": 0.1017780642857143,
"max": 0.19919177142857142,
"count": 66
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4248929000000001,
"min": 1.3943424,
"max": 2.6634422500000006,
"count": 66
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00018762862214285718,
"min": 0.00018762862214285718,
"max": 0.009919257965714285,
"count": 66
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0026268007100000005,
"min": 0.0026268007100000005,
"max": 0.12635788077500001,
"count": 66
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008229024708271027,
"min": 0.007826493121683598,
"max": 0.4388757348060608,
"count": 66
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11520634591579437,
"min": 0.10957090556621552,
"max": 3.0721302032470703,
"count": 66
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 220.4962962962963,
"min": 203.6993006993007,
"max": 999.0,
"count": 66
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29767.0,
"min": 15984.0,
"max": 33082.0,
"count": 66
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7795036924106102,
"min": -1.0000000521540642,
"max": 1.7966783059226883,
"count": 66
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 240.2329984754324,
"min": -31.998801663517952,
"max": 267.112998560071,
"count": 66
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7795036924106102,
"min": -1.0000000521540642,
"max": 1.7966783059226883,
"count": 66
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 240.2329984754324,
"min": -31.998801663517952,
"max": 267.112998560071,
"count": 66
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.01889126900124312,
"min": 0.01764048443792935,
"max": 9.110685833729804,
"count": 66
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.550321315167821,
"min": 2.4585653777612606,
"max": 145.77097333967686,
"count": 66
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 66
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 66
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1673620315",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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",
"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": "1673624710"
},
"total": 4395.093876395001,
"count": 1,
"self": 0.4241593910010124,
"children": {
"run_training.setup": {
"total": 0.11400399699999753,
"count": 1,
"self": 0.11400399699999753
},
"TrainerController.start_learning": {
"total": 4394.555713007,
"count": 1,
"self": 2.4842224960120802,
"children": {
"TrainerController._reset_env": {
"total": 9.521725463999985,
"count": 1,
"self": 9.521725463999985
},
"TrainerController.advance": {
"total": 4382.457732749988,
"count": 129598,
"self": 2.6425799711014406,
"children": {
"env_step": {
"total": 3061.4848862749936,
"count": 129598,
"self": 2858.441981782051,
"children": {
"SubprocessEnvManager._take_step": {
"total": 201.47308610696194,
"count": 129598,
"self": 8.28559791601623,
"children": {
"TorchPolicy.evaluate": {
"total": 193.18748819094571,
"count": 125056,
"self": 65.43051573290359,
"children": {
"TorchPolicy.sample_actions": {
"total": 127.75697245804213,
"count": 125056,
"self": 127.75697245804213
}
}
}
}
},
"workers": {
"total": 1.5698183859809092,
"count": 129598,
"self": 0.0,
"children": {
"worker_root": {
"total": 4386.382064792113,
"count": 129598,
"is_parallel": true,
"self": 1720.7778098162344,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005104625999990731,
"count": 1,
"is_parallel": true,
"self": 0.0029805739999915204,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021240519999992102,
"count": 8,
"is_parallel": true,
"self": 0.0021240519999992102
}
}
},
"UnityEnvironment.step": {
"total": 0.043102734999990844,
"count": 1,
"is_parallel": true,
"self": 0.0004890889999842329,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004396570000153588,
"count": 1,
"is_parallel": true,
"self": 0.0004396570000153588
},
"communicator.exchange": {
"total": 0.04056606300002841,
"count": 1,
"is_parallel": true,
"self": 0.04056606300002841
},
"steps_from_proto": {
"total": 0.0016079259999628448,
"count": 1,
"is_parallel": true,
"self": 0.00040968699994436975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001198239000018475,
"count": 8,
"is_parallel": true,
"self": 0.001198239000018475
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2665.6042549758786,
"count": 129597,
"is_parallel": true,
"self": 55.36691782582648,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 42.91561223704417,
"count": 129597,
"is_parallel": true,
"self": 42.91561223704417
},
"communicator.exchange": {
"total": 2367.501065414963,
"count": 129597,
"is_parallel": true,
"self": 2367.501065414963
},
"steps_from_proto": {
"total": 199.82065949804507,
"count": 129597,
"is_parallel": true,
"self": 43.54814323008969,
"children": {
"_process_rank_one_or_two_observation": {
"total": 156.27251626795538,
"count": 1036776,
"is_parallel": true,
"self": 156.27251626795538
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1318.3302665038937,
"count": 129598,
"self": 4.844167717961227,
"children": {
"process_trajectory": {
"total": 292.83526258293523,
"count": 129598,
"self": 292.46484278993603,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3704197929992006,
"count": 4,
"self": 0.3704197929992006
}
}
},
"_update_policy": {
"total": 1020.6508362029972,
"count": 917,
"self": 392.9678273220085,
"children": {
"TorchPPOOptimizer.update": {
"total": 627.6830088809887,
"count": 45675,
"self": 627.6830088809887
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.609995347796939e-07,
"count": 1,
"self": 8.609995347796939e-07
},
"TrainerController._save_models": {
"total": 0.09203143600007024,
"count": 1,
"self": 0.0015091730001586257,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09052226299991162,
"count": 1,
"self": 0.09052226299991162
}
}
}
}
}
}
}