|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.35972166061401367, |
|
"min": 0.3565860390663147, |
|
"max": 1.5224719047546387, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 10780.138671875, |
|
"min": 10691.8759765625, |
|
"max": 46185.70703125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989984.0, |
|
"min": 29952.0, |
|
"max": 989984.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989984.0, |
|
"min": 29952.0, |
|
"max": 989984.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5370248556137085, |
|
"min": -0.12579688429832458, |
|
"max": 0.5833202004432678, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 147.6818389892578, |
|
"min": -30.191251754760742, |
|
"max": 160.41305541992188, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.031210899353027344, |
|
"min": -0.006476766895502806, |
|
"max": 0.3466683328151703, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 8.58299732208252, |
|
"min": -1.7875876426696777, |
|
"max": 82.16039276123047, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06833592539756554, |
|
"min": 0.06616419819118792, |
|
"max": 0.07431297314979139, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9567029555659176, |
|
"min": 0.5201908120485398, |
|
"max": 1.0904272710858827, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01391457947655366, |
|
"min": 0.0004788915977658381, |
|
"max": 0.017145698353401493, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.19480411267175124, |
|
"min": 0.004310024379892543, |
|
"max": 0.2400397769476209, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.293461854592854e-06, |
|
"min": 7.293461854592854e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010210846596429996, |
|
"min": 0.00010210846596429996, |
|
"max": 0.003259038213653999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10243112142857144, |
|
"min": 0.10243112142857144, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4340357000000001, |
|
"min": 1.3886848, |
|
"max": 2.4426947, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025286903071428563, |
|
"min": 0.00025286903071428563, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003540166429999999, |
|
"min": 0.003540166429999999, |
|
"max": 0.1086559654, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.011222408153116703, |
|
"min": 0.010862556286156178, |
|
"max": 0.3340176045894623, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.157113716006279, |
|
"min": 0.15207578241825104, |
|
"max": 2.338123321533203, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 349.03409090909093, |
|
"min": 318.9021739130435, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30715.0, |
|
"min": 15984.0, |
|
"max": 32574.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.5626666459372673, |
|
"min": -1.0000000521540642, |
|
"max": 1.6158565052015625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 135.95199819654226, |
|
"min": -30.606001675128937, |
|
"max": 148.65879847854376, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.5626666459372673, |
|
"min": -1.0000000521540642, |
|
"max": 1.6158565052015625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 135.95199819654226, |
|
"min": -30.606001675128937, |
|
"max": 148.65879847854376, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.04013483056790381, |
|
"min": 0.03711713711693491, |
|
"max": 6.398833961226046, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.491730259407632, |
|
"min": 3.4147766147580114, |
|
"max": 102.38134337961674, |
|
"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": "1680802200", |
|
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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=PyramidsTraining --no-graphics", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1680804397" |
|
}, |
|
"total": 2196.670589209, |
|
"count": 1, |
|
"self": 0.5422697680000965, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10669066699995255, |
|
"count": 1, |
|
"self": 0.10669066699995255 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2196.021628774, |
|
"count": 1, |
|
"self": 1.3620396650198927, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.7474637779999966, |
|
"count": 1, |
|
"self": 3.7474637779999966 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2190.81873468498, |
|
"count": 63861, |
|
"self": 1.4652675569573148, |
|
"children": { |
|
"env_step": { |
|
"total": 1571.241082956993, |
|
"count": 63861, |
|
"self": 1465.26832421799, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 105.13937943501884, |
|
"count": 63861, |
|
"self": 4.714956376054488, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 100.42442305896435, |
|
"count": 62544, |
|
"self": 100.42442305896435 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8333793039842021, |
|
"count": 63861, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2190.7504840089928, |
|
"count": 63861, |
|
"is_parallel": true, |
|
"self": 836.0714021770127, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0017663149999975758, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005536370001095747, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001212677999888001, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001212677999888001 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.0879787560000409, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0010314880000805715, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00046897199996465133, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00046897199996465133 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.07874866299999894, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.07874866299999894 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.007729632999996738, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004151890000230196, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.007314443999973719, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.007314443999973719 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1354.67908183198, |
|
"count": 63860, |
|
"is_parallel": true, |
|
"self": 32.6258467839707, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 23.776589154994838, |
|
"count": 63860, |
|
"is_parallel": true, |
|
"self": 23.776589154994838 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1203.2959088620012, |
|
"count": 63860, |
|
"is_parallel": true, |
|
"self": 1203.2959088620012 |
|
}, |
|
"steps_from_proto": { |
|
"total": 94.98073703101352, |
|
"count": 63860, |
|
"is_parallel": true, |
|
"self": 20.182399142994484, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 74.79833788801903, |
|
"count": 510880, |
|
"is_parallel": true, |
|
"self": 74.79833788801903 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 618.1123841710296, |
|
"count": 63861, |
|
"self": 2.6007809680270384, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 103.63452865300411, |
|
"count": 63861, |
|
"self": 103.29642421100385, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.33810444200025813, |
|
"count": 2, |
|
"self": 0.33810444200025813 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 511.87707454999844, |
|
"count": 445, |
|
"self": 327.1861049030166, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 184.69096964698184, |
|
"count": 22839, |
|
"self": 184.69096964698184 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.899999895424116e-07, |
|
"count": 1, |
|
"self": 9.899999895424116e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09338965599999938, |
|
"count": 1, |
|
"self": 0.0016669649999130343, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09172269100008634, |
|
"count": 1, |
|
"self": 0.09172269100008634 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |