|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.9048982858657837, |
|
"min": 0.8630123138427734, |
|
"max": 1.480499505996704, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 27089.03515625, |
|
"min": 26304.615234375, |
|
"max": 44912.43359375, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479889.0, |
|
"min": 29952.0, |
|
"max": 479889.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479889.0, |
|
"min": 29952.0, |
|
"max": 479889.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.006121624726802111, |
|
"min": -0.11610650271177292, |
|
"max": -0.006121624726802111, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -1.4875547885894775, |
|
"min": -27.517240524291992, |
|
"max": -1.4875547885894775, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.015242651104927063, |
|
"min": 0.010956994257867336, |
|
"max": 0.1891762763261795, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 3.7039642333984375, |
|
"min": 2.6625494956970215, |
|
"max": 45.59148406982422, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06875073442660705, |
|
"min": 0.06606720322118453, |
|
"max": 0.07221163249263396, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9625102819724988, |
|
"min": 0.5054814274484377, |
|
"max": 0.9903795158923672, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.004634330534579417, |
|
"min": 0.00016639921555936286, |
|
"max": 0.005201913420101066, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.06488062748411184, |
|
"min": 0.00232958901783108, |
|
"max": 0.06488062748411184, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.1327907176442854e-05, |
|
"min": 2.1327907176442854e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00029859070047019996, |
|
"min": 0.00029859070047019996, |
|
"max": 0.0030855794714735995, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10710927142857143, |
|
"min": 0.10710927142857143, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4995298000000001, |
|
"min": 1.3773696000000002, |
|
"max": 2.3382564000000006, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007202162157142859, |
|
"min": 0.0007202162157142859, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.010083027020000003, |
|
"min": 0.010083027020000003, |
|
"max": 0.10287978735999999, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.019994299858808517, |
|
"min": 0.019994299858808517, |
|
"max": 0.34004443883895874, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.27992019057273865, |
|
"min": 0.27992019057273865, |
|
"max": 2.3803110122680664, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 896.75, |
|
"min": 896.75, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28696.0, |
|
"min": 15984.0, |
|
"max": 33547.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.334687547525391, |
|
"min": -1.0000000521540642, |
|
"max": -0.334687547525391, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -10.710001520812511, |
|
"min": -31.99320164322853, |
|
"max": -9.804601162672043, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.334687547525391, |
|
"min": -1.0000000521540642, |
|
"max": -0.334687547525391, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -10.710001520812511, |
|
"min": -31.99320164322853, |
|
"max": -9.804601162672043, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.18418438349908683, |
|
"min": 0.18418438349908683, |
|
"max": 6.891527065541595, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 5.893900271970779, |
|
"min": 5.893900271970779, |
|
"max": 110.26443304866552, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1658231315", |
|
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 01 --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": "1658232999" |
|
}, |
|
"total": 1683.2569665990004, |
|
"count": 1, |
|
"self": 0.6526446279995071, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.05811048000032315, |
|
"count": 1, |
|
"self": 0.05811048000032315 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1682.5462114910006, |
|
"count": 1, |
|
"self": 1.3328430269239107, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 12.270035740999447, |
|
"count": 1, |
|
"self": 12.270035740999447 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1668.8032660030776, |
|
"count": 31575, |
|
"self": 1.4607955001429218, |
|
"children": { |
|
"env_step": { |
|
"total": 1003.186300423994, |
|
"count": 31575, |
|
"self": 922.3573002959856, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 80.03104235199498, |
|
"count": 31575, |
|
"self": 4.005417806960395, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 76.02562454503459, |
|
"count": 31305, |
|
"self": 17.29501512803381, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 58.73060941700078, |
|
"count": 31305, |
|
"self": 58.73060941700078 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7979577760133907, |
|
"count": 31575, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1678.795608782979, |
|
"count": 31575, |
|
"is_parallel": true, |
|
"self": 851.0906930279143, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.00795967500016559, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0058327610004198505, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0021269139997457387, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0021269139997457387 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.13274759799969615, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007238069983941386, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005362480005715042, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005362480005715042 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.1292546909999146, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.1292546909999146 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0022328520008159103, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006217919999471633, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001611060000868747, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001611060000868747 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 827.7049157550646, |
|
"count": 31574, |
|
"is_parallel": true, |
|
"self": 21.871855172159485, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 13.070093787880069, |
|
"count": 31574, |
|
"is_parallel": true, |
|
"self": 13.070093787880069 |
|
}, |
|
"communicator.exchange": { |
|
"total": 726.7314116400648, |
|
"count": 31574, |
|
"is_parallel": true, |
|
"self": 726.7314116400648 |
|
}, |
|
"steps_from_proto": { |
|
"total": 66.03155515496019, |
|
"count": 31574, |
|
"is_parallel": true, |
|
"self": 18.291526737627464, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 47.740028417332724, |
|
"count": 252592, |
|
"is_parallel": true, |
|
"self": 47.740028417332724 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 664.1561700789407, |
|
"count": 31575, |
|
"self": 2.703831531988726, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 117.69387489495148, |
|
"count": 31575, |
|
"self": 117.49551247595173, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.19836241899974993, |
|
"count": 1, |
|
"self": 0.19836241899974993 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 543.7584636520005, |
|
"count": 217, |
|
"self": 142.38259147003646, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 401.37587218196404, |
|
"count": 11391, |
|
"self": 401.37587218196404 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.3939998098067008e-06, |
|
"count": 1, |
|
"self": 1.3939998098067008e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.14006532599978527, |
|
"count": 1, |
|
"self": 0.0030272419999164413, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.13703808399986883, |
|
"count": 1, |
|
"self": 0.13703808399986883 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |