|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.4242943525314331, |
|
"min": 0.4242943525314331, |
|
"max": 1.4093272686004639, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 21235.083984375, |
|
"min": 21235.083984375, |
|
"max": 71909.515625, |
|
"count": 20 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 999992.0, |
|
"min": 49981.0, |
|
"max": 999992.0, |
|
"count": 20 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 999992.0, |
|
"min": 49981.0, |
|
"max": 999992.0, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5126861333847046, |
|
"min": -0.1227642223238945, |
|
"max": 0.5126861333847046, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 231.734130859375, |
|
"min": -49.105690002441406, |
|
"max": 231.734130859375, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.03463253006339073, |
|
"min": 0.003584560938179493, |
|
"max": 0.40515077114105225, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 15.65390396118164, |
|
"min": 1.466085433959961, |
|
"max": 162.060302734375, |
|
"count": 20 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06863634869942971, |
|
"min": 0.06615531648147355, |
|
"max": 0.07220145481884185, |
|
"count": 20 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.6472723687863131, |
|
"min": 0.9265794129222367, |
|
"max": 1.7328349156522045, |
|
"count": 20 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.014418069885828623, |
|
"min": 0.000880262116700447, |
|
"max": 0.015187545013985405, |
|
"count": 20 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.34603367725988693, |
|
"min": 0.019365766567409834, |
|
"max": 0.3645010803356497, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.340372553241669e-06, |
|
"min": 7.340372553241669e-06, |
|
"max": 0.0002916442643237077, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00017616894127780005, |
|
"min": 0.00017616894127780005, |
|
"max": 0.005452137382620999, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10244675833333335, |
|
"min": 0.10244675833333335, |
|
"max": 0.19721475384615386, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 2.4587222000000004, |
|
"min": 2.4587222000000004, |
|
"max": 4.0837108, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002544311575000001, |
|
"min": 0.0002544311575000001, |
|
"max": 0.00972175390923077, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.006106347780000002, |
|
"min": 0.006106347780000002, |
|
"max": 0.1817761621, |
|
"count": 20 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.012546318583190441, |
|
"min": 0.012509429827332497, |
|
"max": 0.2747448980808258, |
|
"count": 20 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.30111163854599, |
|
"min": 0.28771689534187317, |
|
"max": 3.571683645248413, |
|
"count": 20 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 363.55, |
|
"min": 363.55, |
|
"max": 997.6041666666666, |
|
"count": 20 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 50897.0, |
|
"min": 47044.0, |
|
"max": 53410.0, |
|
"count": 20 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.5332891867636778, |
|
"min": -0.9569167188989619, |
|
"max": 1.5332891867636778, |
|
"count": 20 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 213.1271969601512, |
|
"min": -45.93200250715017, |
|
"max": 213.1271969601512, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.5332891867636778, |
|
"min": -0.9569167188989619, |
|
"max": 1.5332891867636778, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 213.1271969601512, |
|
"min": -45.93200250715017, |
|
"max": 213.1271969601512, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.0480055328456035, |
|
"min": 0.0480055328456035, |
|
"max": 3.7991478253776827, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 6.672769065538887, |
|
"min": 6.190021476068068, |
|
"max": 182.35909561812878, |
|
"count": 20 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 20 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 20 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1661038628", |
|
"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 --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": "1661040597" |
|
}, |
|
"total": 1968.2627793349998, |
|
"count": 1, |
|
"self": 0.47653668299972196, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04291885099996762, |
|
"count": 1, |
|
"self": 0.04291885099996762 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1967.743323801, |
|
"count": 1, |
|
"self": 1.329606279989548, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.354747836000115, |
|
"count": 1, |
|
"self": 9.354747836000115 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1956.9653390600104, |
|
"count": 63631, |
|
"self": 1.3999839279820208, |
|
"children": { |
|
"env_step": { |
|
"total": 1263.8576822490381, |
|
"count": 63631, |
|
"self": 1162.9751128650016, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 100.17732810501343, |
|
"count": 63631, |
|
"self": 4.5819465401159505, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 95.59538156489748, |
|
"count": 62558, |
|
"self": 34.02026225591794, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 61.57511930897954, |
|
"count": 62558, |
|
"self": 61.57511930897954 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7052412790230846, |
|
"count": 63631, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1963.731069005034, |
|
"count": 63631, |
|
"is_parallel": true, |
|
"self": 900.5146379980501, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.006084160000000338, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004933731999926749, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001150428000073589, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001150428000073589 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04638965399999506, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005272749999676307, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00044776000004276284, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00044776000004276284 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.0438198189999639, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0438198189999639 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015948000000207685, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00040331900004275667, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011914809999780118, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011914809999780118 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1063.2164310069838, |
|
"count": 63630, |
|
"is_parallel": true, |
|
"self": 26.995305528965446, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.210597863977227, |
|
"count": 63630, |
|
"is_parallel": true, |
|
"self": 22.210597863977227 |
|
}, |
|
"communicator.exchange": { |
|
"total": 923.5843695849821, |
|
"count": 63630, |
|
"is_parallel": true, |
|
"self": 923.5843695849821 |
|
}, |
|
"steps_from_proto": { |
|
"total": 90.42615802905902, |
|
"count": 63630, |
|
"is_parallel": true, |
|
"self": 22.29651465890629, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 68.12964337015273, |
|
"count": 509040, |
|
"is_parallel": true, |
|
"self": 68.12964337015273 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 691.7076728829902, |
|
"count": 63631, |
|
"self": 2.4560120970388652, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 158.03512920394815, |
|
"count": 63631, |
|
"self": 157.71700489194836, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.31812431199978164, |
|
"count": 2, |
|
"self": 0.31812431199978164 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 531.2165315820032, |
|
"count": 449, |
|
"self": 212.32515604799391, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 318.8913755340093, |
|
"count": 22854, |
|
"self": 318.8913755340093 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.190000148199033e-06, |
|
"count": 1, |
|
"self": 1.190000148199033e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09362943499991161, |
|
"count": 1, |
|
"self": 0.001927646999774879, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09170178800013673, |
|
"count": 1, |
|
"self": 0.09170178800013673 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |