ppo-Pyramids_v1 / run_logs /timers.json
ben-yu's picture
First Push
21b174d
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3715488612651825,
"min": 0.36983180046081543,
"max": 1.4425631761550903,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11081.0732421875,
"min": 11081.0732421875,
"max": 43761.59765625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989977.0,
"min": 29952.0,
"max": 989977.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989977.0,
"min": 29952.0,
"max": 989977.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5457786321640015,
"min": -0.1142708882689476,
"max": 0.5482723712921143,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 151.18067932128906,
"min": -27.539283752441406,
"max": 151.18067932128906,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.02749679982662201,
"min": -0.11100063472986221,
"max": 0.3255608081817627,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -7.616613388061523,
"min": -29.08216667175293,
"max": 77.15791320800781,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06916052128681692,
"min": 0.06548825904243712,
"max": 0.07298864527963037,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9682472980154369,
"min": 0.487985318918022,
"max": 1.0546870516092681,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015048145549371839,
"min": 0.0009376245224151857,
"max": 0.01567572599567558,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21067403769120574,
"min": 0.0065633716569063,
"max": 0.2351358899351337,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.373326113685711e-06,
"min": 7.373326113685711e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010322656559159995,
"min": 0.00010322656559159995,
"max": 0.0033760153746615995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10245774285714286,
"min": 0.10245774285714286,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4344084000000001,
"min": 1.3691136000000002,
"max": 2.4847339,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025552851142857135,
"min": 0.00025552851142857135,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035773991599999987,
"min": 0.0035773991599999987,
"max": 0.11255130615999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014001617208123207,
"min": 0.013551115989685059,
"max": 0.4308586120605469,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1960226446390152,
"min": 0.18971562385559082,
"max": 3.016010284423828,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 362.7738095238095,
"min": 334.60227272727275,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30473.0,
"min": 15984.0,
"max": 32796.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.589597596121686,
"min": -1.0000000521540642,
"max": 1.601497485116124,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 133.5261980742216,
"min": -32.000001668930054,
"max": 138.55279825627804,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.589597596121686,
"min": -1.0000000521540642,
"max": 1.601497485116124,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 133.5261980742216,
"min": -32.000001668930054,
"max": 138.55279825627804,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05227665613243256,
"min": 0.04689791191379878,
"max": 8.541909467428923,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.3912391151243355,
"min": 4.113862060185056,
"max": 136.67055147886276,
"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": "1675665166",
"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": "1675667427"
},
"total": 2260.6745307789997,
"count": 1,
"self": 0.7359036319999177,
"children": {
"run_training.setup": {
"total": 0.09867781699995248,
"count": 1,
"self": 0.09867781699995248
},
"TrainerController.start_learning": {
"total": 2259.83994933,
"count": 1,
"self": 1.336246014012886,
"children": {
"TrainerController._reset_env": {
"total": 6.997904989000062,
"count": 1,
"self": 6.997904989000062
},
"TrainerController.advance": {
"total": 2251.364052915986,
"count": 63764,
"self": 1.351642351904502,
"children": {
"env_step": {
"total": 1511.1522964770027,
"count": 63764,
"self": 1396.0377479679278,
"children": {
"SubprocessEnvManager._take_step": {
"total": 114.290118215029,
"count": 63764,
"self": 4.896605586970054,
"children": {
"TorchPolicy.evaluate": {
"total": 109.39351262805894,
"count": 62559,
"self": 36.6706195650961,
"children": {
"TorchPolicy.sample_actions": {
"total": 72.72289306296284,
"count": 62559,
"self": 72.72289306296284
}
}
}
}
},
"workers": {
"total": 0.8244302940458965,
"count": 63764,
"self": 0.0,
"children": {
"worker_root": {
"total": 2254.9043770159387,
"count": 63764,
"is_parallel": true,
"self": 972.439911812922,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017589219999081251,
"count": 1,
"is_parallel": true,
"self": 0.0006871049997698719,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010718170001382532,
"count": 8,
"is_parallel": true,
"self": 0.0010718170001382532
}
}
},
"UnityEnvironment.step": {
"total": 0.055444565000016155,
"count": 1,
"is_parallel": true,
"self": 0.0005075239998859615,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045467700010703993,
"count": 1,
"is_parallel": true,
"self": 0.00045467700010703993
},
"communicator.exchange": {
"total": 0.052768887999945946,
"count": 1,
"is_parallel": true,
"self": 0.052768887999945946
},
"steps_from_proto": {
"total": 0.0017134760000772076,
"count": 1,
"is_parallel": true,
"self": 0.00046598200037806237,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012474939996991452,
"count": 8,
"is_parallel": true,
"self": 0.0012474939996991452
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1282.4644652030167,
"count": 63763,
"is_parallel": true,
"self": 27.41633015104253,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.8429088469652,
"count": 63763,
"is_parallel": true,
"self": 22.8429088469652
},
"communicator.exchange": {
"total": 1129.831404154091,
"count": 63763,
"is_parallel": true,
"self": 1129.831404154091
},
"steps_from_proto": {
"total": 102.37382205091808,
"count": 63763,
"is_parallel": true,
"self": 22.704234859886355,
"children": {
"_process_rank_one_or_two_observation": {
"total": 79.66958719103172,
"count": 510104,
"is_parallel": true,
"self": 79.66958719103172
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 738.8601140870787,
"count": 63764,
"self": 2.4270999070213293,
"children": {
"process_trajectory": {
"total": 167.80470018905567,
"count": 63764,
"self": 167.56158315905554,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2431170300001213,
"count": 2,
"self": 0.2431170300001213
}
}
},
"_update_policy": {
"total": 568.6283139910017,
"count": 446,
"self": 222.1681439399913,
"children": {
"TorchPPOOptimizer.update": {
"total": 346.46017005101044,
"count": 22815,
"self": 346.46017005101044
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2640002751140855e-06,
"count": 1,
"self": 1.2640002751140855e-06
},
"TrainerController._save_models": {
"total": 0.14174414700028137,
"count": 1,
"self": 0.002027446000283817,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13971670099999756,
"count": 1,
"self": 0.13971670099999756
}
}
}
}
}
}
}