|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.2793021500110626, |
|
"min": 0.2669001519680023, |
|
"max": 1.4737768173217773, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 8423.7529296875, |
|
"min": 7927.6513671875, |
|
"max": 44708.4921875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989897.0, |
|
"min": 29952.0, |
|
"max": 989897.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989897.0, |
|
"min": 29952.0, |
|
"max": 989897.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.3035065531730652, |
|
"min": -0.25373733043670654, |
|
"max": 0.39500167965888977, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 79.2152099609375, |
|
"min": -60.13574981689453, |
|
"max": 103.0954360961914, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.018861427903175354, |
|
"min": -0.03203427791595459, |
|
"max": 0.33702903985977173, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.922832489013672, |
|
"min": -8.1046724319458, |
|
"max": 79.87588500976562, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07013857732540815, |
|
"min": 0.06387643649892397, |
|
"max": 0.07231759942106254, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9819400825557142, |
|
"min": 0.4924415605635805, |
|
"max": 1.0822687595182305, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.009247080290584736, |
|
"min": 0.0027392577851204384, |
|
"max": 0.013160183627492406, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.1294591240681863, |
|
"min": 0.029942923520890112, |
|
"max": 0.18424257078489367, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.475433222507142e-06, |
|
"min": 7.475433222507142e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0001046560651151, |
|
"min": 0.0001046560651151, |
|
"max": 0.0036334210888597, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10249177857142858, |
|
"min": 0.10249177857142858, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4348849000000001, |
|
"min": 1.3886848, |
|
"max": 2.6111403, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002589286792857143, |
|
"min": 0.0002589286792857143, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036250015100000002, |
|
"min": 0.0036250015100000002, |
|
"max": 0.12113291597000002, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.007961527444422245, |
|
"min": 0.0077878315933048725, |
|
"max": 0.37108084559440613, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.11146137863397598, |
|
"min": 0.10902964323759079, |
|
"max": 2.5975658893585205, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 536.8867924528302, |
|
"min": 455.46774193548384, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28455.0, |
|
"min": 15984.0, |
|
"max": 33173.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.0101433692956872, |
|
"min": -1.0000000521540642, |
|
"max": 1.4252792837034012, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 53.53759857267141, |
|
"min": -28.36120170354843, |
|
"max": 85.20899822562933, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.0101433692956872, |
|
"min": -1.0000000521540642, |
|
"max": 1.4252792837034012, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 53.53759857267141, |
|
"min": -28.36120170354843, |
|
"max": 85.20899822562933, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.04472490050411236, |
|
"min": 0.039390035072975824, |
|
"max": 7.69922630675137, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.370419726717955, |
|
"min": 2.284622034232598, |
|
"max": 123.18762090802193, |
|
"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": "1677070251", |
|
"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": "1677072452" |
|
}, |
|
"total": 2200.83879773, |
|
"count": 1, |
|
"self": 0.4255042410004535, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10844333499971981, |
|
"count": 1, |
|
"self": 0.10844333499971981 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2200.3048501539997, |
|
"count": 1, |
|
"self": 1.4143607370192512, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 7.164373210000122, |
|
"count": 1, |
|
"self": 7.164373210000122 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2191.6334381109796, |
|
"count": 63726, |
|
"self": 1.36907996007767, |
|
"children": { |
|
"env_step": { |
|
"total": 1467.5882985889566, |
|
"count": 63726, |
|
"self": 1358.2831447449703, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 108.49525896993828, |
|
"count": 63726, |
|
"self": 4.470590628952323, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 104.02466834098595, |
|
"count": 62569, |
|
"self": 35.047998551965065, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 68.97666978902089, |
|
"count": 62569, |
|
"self": 68.97666978902089 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.809894874048041, |
|
"count": 63726, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2195.4831710010053, |
|
"count": 63726, |
|
"is_parallel": true, |
|
"self": 948.6198551490315, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0018395790002614376, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006733659997735231, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011662130004879145, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011662130004879145 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.09864290699988487, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005714690000786504, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004471239999475074, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004471239999475074 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.09598905899974852, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.09598905899974852 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016352550001101918, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004240670004946878, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001211187999615504, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001211187999615504 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1246.8633158519738, |
|
"count": 63725, |
|
"is_parallel": true, |
|
"self": 30.66920036386, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.881645829097124, |
|
"count": 63725, |
|
"is_parallel": true, |
|
"self": 22.881645829097124 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1100.8736686969664, |
|
"count": 63725, |
|
"is_parallel": true, |
|
"self": 1100.8736686969664 |
|
}, |
|
"steps_from_proto": { |
|
"total": 92.43880096205021, |
|
"count": 63725, |
|
"is_parallel": true, |
|
"self": 21.37945493615507, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 71.05934602589514, |
|
"count": 509800, |
|
"is_parallel": true, |
|
"self": 71.05934602589514 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 722.6760595619453, |
|
"count": 63726, |
|
"self": 2.597152909952456, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 159.0079268979939, |
|
"count": 63726, |
|
"self": 158.8294966269941, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.17843027099979736, |
|
"count": 2, |
|
"self": 0.17843027099979736 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 561.0709797539989, |
|
"count": 458, |
|
"self": 217.4377574700443, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 343.63322228395464, |
|
"count": 22788, |
|
"self": 343.63322228395464 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.85000042419415e-07, |
|
"count": 1, |
|
"self": 9.85000042419415e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09267711100073939, |
|
"count": 1, |
|
"self": 0.001372718000311579, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09130439300042781, |
|
"count": 1, |
|
"self": 0.09130439300042781 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |