|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.1831962913274765, |
|
"min": 0.1831962913274765, |
|
"max": 1.4030972719192505, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 5443.12841796875, |
|
"min": 5443.12841796875, |
|
"max": 42564.359375, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999897.0, |
|
"min": 29957.0, |
|
"max": 2999897.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999897.0, |
|
"min": 29957.0, |
|
"max": 2999897.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.8675899505615234, |
|
"min": -0.10322670638561249, |
|
"max": 0.8675899505615234, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 267.21771240234375, |
|
"min": -24.774410247802734, |
|
"max": 267.21771240234375, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.0021614315919578075, |
|
"min": -0.009575147181749344, |
|
"max": 0.3840174078941345, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -0.6657209396362305, |
|
"min": -2.8246684074401855, |
|
"max": 91.3961410522461, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06677757072542419, |
|
"min": 0.062460236586048275, |
|
"max": 0.07272326924275326, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9348859901559385, |
|
"min": 0.4989583194423092, |
|
"max": 1.0804470503353512, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015470774749354902, |
|
"min": 0.00014103356808186499, |
|
"max": 0.016758141704771082, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.21659084649096863, |
|
"min": 0.0018334363850642447, |
|
"max": 0.25137212557156624, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.4781995073000018e-06, |
|
"min": 1.4781995073000018e-06, |
|
"max": 0.00029841272910051907, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.0694793102200025e-05, |
|
"min": 2.0694793102200025e-05, |
|
"max": 0.0040526196491267995, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10049269999999999, |
|
"min": 0.10049269999999999, |
|
"max": 0.19947090952380955, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4068977999999999, |
|
"min": 1.3962963666666668, |
|
"max": 2.7508732000000005, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 5.922073000000008e-05, |
|
"min": 5.922073000000008e-05, |
|
"max": 0.009947143861428571, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008290902200000011, |
|
"min": 0.0008290902200000011, |
|
"max": 0.13509223268, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.0050178999081254005, |
|
"min": 0.0050178999081254005, |
|
"max": 0.28419381380081177, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.07025060057640076, |
|
"min": 0.07025060057640076, |
|
"max": 1.9893567562103271, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 210.3877551020408, |
|
"min": 205.31034482758622, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30927.0, |
|
"min": 16628.0, |
|
"max": 32730.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.77600543180696, |
|
"min": -0.9997226321889509, |
|
"max": 1.7872014792997446, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 261.07279847562313, |
|
"min": -30.991401597857475, |
|
"max": 261.07279847562313, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.77600543180696, |
|
"min": -0.9997226321889509, |
|
"max": 1.7872014792997446, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 261.07279847562313, |
|
"min": -30.991401597857475, |
|
"max": 261.07279847562313, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.011044202118911654, |
|
"min": 0.011044202118911654, |
|
"max": 5.234463107169551, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 1.623497711480013, |
|
"min": 1.5349532740656286, |
|
"max": 88.98587282188237, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1678896937", |
|
"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=Pyramids Training --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": "1678903978" |
|
}, |
|
"total": 7041.621897225001, |
|
"count": 1, |
|
"self": 0.48829447999924014, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10121478100018066, |
|
"count": 1, |
|
"self": 0.10121478100018066 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 7041.032387964001, |
|
"count": 1, |
|
"self": 4.279513499911445, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 7.137056819999998, |
|
"count": 1, |
|
"self": 7.137056819999998 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 7029.51810427409, |
|
"count": 194416, |
|
"self": 4.604560456399668, |
|
"children": { |
|
"env_step": { |
|
"total": 5187.086400418697, |
|
"count": 194416, |
|
"self": 4860.421685129949, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 324.06522057471784, |
|
"count": 194416, |
|
"self": 14.123216512640738, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 309.9420040620771, |
|
"count": 187542, |
|
"self": 309.9420040620771 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.599494714030243, |
|
"count": 194416, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 7025.91826345774, |
|
"count": 194416, |
|
"is_parallel": true, |
|
"self": 2517.8532818880376, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0024591239998699166, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007148099998630641, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0017443140000068524, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0017443140000068524 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04659869699980845, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000549624999621301, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004763880001519283, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004763880001519283 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04395655899998019, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04395655899998019 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016161250000550353, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003796229998442868, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012365020002107485, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012365020002107485 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 4508.0649815697025, |
|
"count": 194415, |
|
"is_parallel": true, |
|
"self": 93.87945050240432, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 66.91296703207263, |
|
"count": 194415, |
|
"is_parallel": true, |
|
"self": 66.91296703207263 |
|
}, |
|
"communicator.exchange": { |
|
"total": 4071.9833795521085, |
|
"count": 194415, |
|
"is_parallel": true, |
|
"self": 4071.9833795521085 |
|
}, |
|
"steps_from_proto": { |
|
"total": 275.2891844831179, |
|
"count": 194415, |
|
"is_parallel": true, |
|
"self": 59.58703876449408, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 215.7021457186238, |
|
"count": 1555320, |
|
"is_parallel": true, |
|
"self": 215.7021457186238 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1837.827143398993, |
|
"count": 194416, |
|
"self": 8.187124995135946, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 353.0863881128962, |
|
"count": 194416, |
|
"self": 352.4608233808963, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.6255647319999298, |
|
"count": 6, |
|
"self": 0.6255647319999298 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1476.5536302909609, |
|
"count": 1401, |
|
"self": 939.3457707249681, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 537.2078595659927, |
|
"count": 68331, |
|
"self": 537.2078595659927 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.519990271655843e-07, |
|
"count": 1, |
|
"self": 9.519990271655843e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09771241800081043, |
|
"count": 1, |
|
"self": 0.0015371999998023966, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09617521800100803, |
|
"count": 1, |
|
"self": 0.09617521800100803 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |