ppo-Pyramids / run_logs /timers.json
ZhihongDeng's picture
First Push
e39bf74
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.48313814401626587,
"min": 0.4563673138618469,
"max": 1.362297534942627,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14494.14453125,
"min": 13742.1328125,
"max": 41326.65625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989880.0,
"min": 29952.0,
"max": 989880.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989880.0,
"min": 29952.0,
"max": 989880.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.49682486057281494,
"min": -0.1055130735039711,
"max": 0.50117027759552,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 137.6204833984375,
"min": -25.639677047729492,
"max": 139.32533264160156,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.010925655253231525,
"min": -0.016304364427924156,
"max": 0.31473347544670105,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -3.0264065265655518,
"min": -4.255439281463623,
"max": 75.5360336303711,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06978971837100695,
"min": 0.06462127454973857,
"max": 0.07519007139004921,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9770560571940973,
"min": 0.5132396912507328,
"max": 1.052660999460689,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01375036268323906,
"min": 0.00017307829632448528,
"max": 0.015173183950537348,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19250507756534682,
"min": 0.0022500178522183085,
"max": 0.21242457530752287,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.6016903232785715e-06,
"min": 7.6016903232785715e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001064236645259,
"min": 0.0001064236645259,
"max": 0.0031390832536389995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253386428571429,
"min": 0.10253386428571429,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354741,
"min": 1.3691136000000002,
"max": 2.3923712000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002631330421428572,
"min": 0.0002631330421428572,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036838625900000007,
"min": 0.0036838625900000007,
"max": 0.10466146390000002,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008583104237914085,
"min": 0.008583104237914085,
"max": 0.4123249053955078,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1201634556055069,
"min": 0.1201634556055069,
"max": 2.8862743377685547,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 393.44303797468353,
"min": 354.6470588235294,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31082.0,
"min": 15984.0,
"max": 32367.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.454620231650298,
"min": -1.0000000521540642,
"max": 1.5072999774196814,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 114.91499830037355,
"min": -32.000001668930054,
"max": 129.6277980580926,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.454620231650298,
"min": -1.0000000521540642,
"max": 1.5072999774196814,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 114.91499830037355,
"min": -32.000001668930054,
"max": 129.6277980580926,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0348268267387746,
"min": 0.0348268267387746,
"max": 8.704965407028794,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.7513193123631936,
"min": 2.7513193123631936,
"max": 139.2794465124607,
"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": "1676719232",
"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",
"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": "1676721385"
},
"total": 2153.5392263420003,
"count": 1,
"self": 0.5251134519999141,
"children": {
"run_training.setup": {
"total": 0.11205069700008607,
"count": 1,
"self": 0.11205069700008607
},
"TrainerController.start_learning": {
"total": 2152.9020621930003,
"count": 1,
"self": 1.3099804249181943,
"children": {
"TrainerController._reset_env": {
"total": 6.267423355000119,
"count": 1,
"self": 6.267423355000119
},
"TrainerController.advance": {
"total": 2145.2386691340816,
"count": 63590,
"self": 1.3735031710834846,
"children": {
"env_step": {
"total": 1413.7334944069798,
"count": 63590,
"self": 1302.6014805018776,
"children": {
"SubprocessEnvManager._take_step": {
"total": 110.33323588709845,
"count": 63590,
"self": 4.489805975144918,
"children": {
"TorchPolicy.evaluate": {
"total": 105.84342991195354,
"count": 62544,
"self": 35.28521798991096,
"children": {
"TorchPolicy.sample_actions": {
"total": 70.55821192204257,
"count": 62544,
"self": 70.55821192204257
}
}
}
}
},
"workers": {
"total": 0.7987780180037589,
"count": 63590,
"self": 0.0,
"children": {
"worker_root": {
"total": 2148.2744545429387,
"count": 63590,
"is_parallel": true,
"self": 957.0342225729332,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018296560001545004,
"count": 1,
"is_parallel": true,
"self": 0.0006519050007227634,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001177750999431737,
"count": 8,
"is_parallel": true,
"self": 0.001177750999431737
}
}
},
"UnityEnvironment.step": {
"total": 0.04852779900011228,
"count": 1,
"is_parallel": true,
"self": 0.0005201160001888638,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048138100009964546,
"count": 1,
"is_parallel": true,
"self": 0.00048138100009964546
},
"communicator.exchange": {
"total": 0.04591348999974798,
"count": 1,
"is_parallel": true,
"self": 0.04591348999974798
},
"steps_from_proto": {
"total": 0.0016128120000757917,
"count": 1,
"is_parallel": true,
"self": 0.00040446900038659805,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012083429996891937,
"count": 8,
"is_parallel": true,
"self": 0.0012083429996891937
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1191.2402319700054,
"count": 63589,
"is_parallel": true,
"self": 31.441978225867388,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.047296032033046,
"count": 63589,
"is_parallel": true,
"self": 23.047296032033046
},
"communicator.exchange": {
"total": 1043.905448475056,
"count": 63589,
"is_parallel": true,
"self": 1043.905448475056
},
"steps_from_proto": {
"total": 92.8455092370491,
"count": 63589,
"is_parallel": true,
"self": 21.657868089019757,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.18764114802934,
"count": 508712,
"is_parallel": true,
"self": 71.18764114802934
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 730.1316715560183,
"count": 63590,
"self": 2.4504597010022735,
"children": {
"process_trajectory": {
"total": 159.85950921701806,
"count": 63590,
"self": 159.66624245401772,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19326676300033796,
"count": 2,
"self": 0.19326676300033796
}
}
},
"_update_policy": {
"total": 567.821702637998,
"count": 440,
"self": 217.3890746350221,
"children": {
"TorchPPOOptimizer.update": {
"total": 350.4326280029759,
"count": 22830,
"self": 350.4326280029759
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.570004865759984e-07,
"count": 1,
"self": 8.570004865759984e-07
},
"TrainerController._save_models": {
"total": 0.08598842199990031,
"count": 1,
"self": 0.0014692310005557374,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08451919099934457,
"count": 1,
"self": 0.08451919099934457
}
}
}
}
}
}
}