|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.7681760787963867, |
|
"min": 0.7681760787963867, |
|
"max": 1.4983874559402466, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 22996.119140625, |
|
"min": 22996.119140625, |
|
"max": 45455.08203125, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479982.0, |
|
"min": 29936.0, |
|
"max": 479982.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479982.0, |
|
"min": 29936.0, |
|
"max": 479982.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.047144293785095215, |
|
"min": -0.16824981570243835, |
|
"max": 0.001643792144022882, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -11.550352096557617, |
|
"min": -39.875205993652344, |
|
"max": 0.3994414806365967, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.027787940576672554, |
|
"min": 0.027147144079208374, |
|
"max": 0.37708112597465515, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 6.808045387268066, |
|
"min": 6.623903274536133, |
|
"max": 89.36822509765625, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0667500350075997, |
|
"min": 0.0667500350075997, |
|
"max": 0.07322732995417837, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9345004901063957, |
|
"min": 0.4999412314778317, |
|
"max": 1.0251826193584972, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.003961177896098506, |
|
"min": 0.001348132152843453, |
|
"max": 0.007998970108255381, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.055456490545379086, |
|
"min": 0.014829453681277985, |
|
"max": 0.05599279075778767, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.1151635806628563e-05, |
|
"min": 2.1151635806628563e-05, |
|
"max": 0.0002904672031776, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0002961229012927999, |
|
"min": 0.0002961229012927999, |
|
"max": 0.0030857762714080004, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.1070505142857143, |
|
"min": 0.1070505142857143, |
|
"max": 0.19682240000000004, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4987072000000001, |
|
"min": 1.3777568000000002, |
|
"max": 2.4217231999999997, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007143463771428571, |
|
"min": 0.0007143463771428571, |
|
"max": 0.00968255776, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.01000084928, |
|
"min": 0.01000084928, |
|
"max": 0.10288634079999999, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.022521035745739937, |
|
"min": 0.022521035745739937, |
|
"max": 0.40944308042526245, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.3152945041656494, |
|
"min": 0.3152945041656494, |
|
"max": 2.8661015033721924, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 883.4736842105264, |
|
"min": 883.4736842105264, |
|
"max": 984.4117647058823, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 33572.0, |
|
"min": 16735.0, |
|
"max": 33572.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.4101895139013466, |
|
"min": -0.9187879289189974, |
|
"max": -0.4101895139013466, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -15.587201528251171, |
|
"min": -30.320001654326916, |
|
"max": -14.165801465511322, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.4101895139013466, |
|
"min": -0.9187879289189974, |
|
"max": -0.4101895139013466, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -15.587201528251171, |
|
"min": -30.320001654326916, |
|
"max": -14.165801465511322, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.20906067330782352, |
|
"min": 0.20906067330782352, |
|
"max": 8.151594232110416, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 7.944305585697293, |
|
"min": 7.026834661141038, |
|
"max": 138.57710194587708, |
|
"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": "1667189205", |
|
"python_version": "3.7.15 (default, Oct 12 2022, 19:14:55) \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": "1667190208" |
|
}, |
|
"total": 1002.357411273, |
|
"count": 1, |
|
"self": 0.4402678090000336, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.046048018000021784, |
|
"count": 1, |
|
"self": 0.046048018000021784 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1001.871095446, |
|
"count": 1, |
|
"self": 0.6815595759944699, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 8.811629516000039, |
|
"count": 1, |
|
"self": 8.811629516000039 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 992.2868531760055, |
|
"count": 31557, |
|
"self": 0.7441992700405535, |
|
"children": { |
|
"env_step": { |
|
"total": 638.3519582579721, |
|
"count": 31557, |
|
"self": 584.9285537759613, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 53.054358985008435, |
|
"count": 31557, |
|
"self": 2.2635858330012297, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 50.790773152007205, |
|
"count": 31302, |
|
"self": 17.283997622023264, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 33.50677552998394, |
|
"count": 31302, |
|
"self": 33.50677552998394 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.36904549700233247, |
|
"count": 31557, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 999.4888524929919, |
|
"count": 31557, |
|
"is_parallel": true, |
|
"self": 464.98410804801324, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.007496189999983471, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0036057689999324793, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.003890421000050992, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.003890421000050992 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.045700609999983044, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005012359999909677, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00045202799998378396, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00045202799998378396 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04310383000000684, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04310383000000684 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016435160000014548, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00046959800005197394, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011739179999494809, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011739179999494809 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 534.5047444449787, |
|
"count": 31556, |
|
"is_parallel": true, |
|
"self": 14.23569051097786, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 11.574186510994139, |
|
"count": 31556, |
|
"is_parallel": true, |
|
"self": 11.574186510994139 |
|
}, |
|
"communicator.exchange": { |
|
"total": 455.1539682579965, |
|
"count": 31556, |
|
"is_parallel": true, |
|
"self": 455.1539682579965 |
|
}, |
|
"steps_from_proto": { |
|
"total": 53.54089916501022, |
|
"count": 31556, |
|
"is_parallel": true, |
|
"self": 11.96179798099746, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 41.57910118401276, |
|
"count": 252448, |
|
"is_parallel": true, |
|
"self": 41.57910118401276 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 353.19069564799287, |
|
"count": 31557, |
|
"self": 1.1700627269900679, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 79.83144392700206, |
|
"count": 31557, |
|
"self": 79.604940343002, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.22650358400005643, |
|
"count": 1, |
|
"self": 0.22650358400005643 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 272.18918899400074, |
|
"count": 218, |
|
"self": 108.92039344799451, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 163.26879554600623, |
|
"count": 11406, |
|
"self": 163.26879554600623 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1070001164625864e-06, |
|
"count": 1, |
|
"self": 1.1070001164625864e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09105207099992185, |
|
"count": 1, |
|
"self": 0.0016110559997741802, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08944101500014767, |
|
"count": 1, |
|
"self": 0.08944101500014767 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |