|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.172193706035614, |
|
"min": 0.1647656112909317, |
|
"max": 1.4083733558654785, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 5141.01513671875, |
|
"min": 4979.8759765625, |
|
"max": 42724.4140625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999981.0, |
|
"min": 29952.0, |
|
"max": 2999981.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999981.0, |
|
"min": 29952.0, |
|
"max": 2999981.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6161277294158936, |
|
"min": -0.09271835535764694, |
|
"max": 0.6173363924026489, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 174.36415100097656, |
|
"min": -22.530559539794922, |
|
"max": 174.36415100097656, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.014366395771503448, |
|
"min": -1.7395180463790894, |
|
"max": 1.7319082021713257, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -4.065690040588379, |
|
"min": -455.75372314453125, |
|
"max": 453.75994873046875, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.04603456548027074, |
|
"min": 0.04314542232702175, |
|
"max": 0.0513265693273956, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.6905184822040611, |
|
"min": 0.33428702012669026, |
|
"max": 0.7394997566007078, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015738900086532035, |
|
"min": 0.00041164355064317423, |
|
"max": 0.40088433486276437, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.23608350129798053, |
|
"min": 0.004528079057074917, |
|
"max": 5.6123806880787015, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 4.911817311399989e-07, |
|
"min": 4.911817311399989e-07, |
|
"max": 9.946118149120001e-05, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 7.367725967099983e-06, |
|
"min": 7.367725967099983e-06, |
|
"max": 0.0013274454725547, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10049108222222224, |
|
"min": 0.10049108222222224, |
|
"max": 0.19946118095238097, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5073662333333335, |
|
"min": 1.3897045333333333, |
|
"max": 2.8274453000000004, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 5.905911399999989e-05, |
|
"min": 5.905911399999989e-05, |
|
"max": 0.009946171977142856, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008858867099999984, |
|
"min": 0.0008858867099999984, |
|
"max": 0.13276178547, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.026145173236727715, |
|
"min": 0.026145173236727715, |
|
"max": 0.5980517268180847, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.39217761158943176, |
|
"min": 0.36809539794921875, |
|
"max": 4.186362266540527, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 310.4, |
|
"min": 289.4848484848485, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29488.0, |
|
"min": 15984.0, |
|
"max": 34277.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6895999808060496, |
|
"min": -1.0000000521540642, |
|
"max": 1.6911179810762405, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 160.5119981765747, |
|
"min": -32.000001668930054, |
|
"max": 169.11179810762405, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6895999808060496, |
|
"min": -1.0000000521540642, |
|
"max": 1.6911179810762405, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 160.5119981765747, |
|
"min": -32.000001668930054, |
|
"max": 169.11179810762405, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.08286011184835317, |
|
"min": 0.07857821287703701, |
|
"max": 11.01363092660904, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 7.8717106255935505, |
|
"min": 7.174652462999802, |
|
"max": 176.21809482574463, |
|
"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": "1673783626", |
|
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", |
|
"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 --force", |
|
"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": "1673791034" |
|
}, |
|
"total": 7408.060608971001, |
|
"count": 1, |
|
"self": 0.4775461550007094, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11163453599965578, |
|
"count": 1, |
|
"self": 0.11163453599965578 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 7407.4714282800005, |
|
"count": 1, |
|
"self": 5.1130147120175025, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.665063098000246, |
|
"count": 1, |
|
"self": 6.665063098000246 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 7395.578573279985, |
|
"count": 192507, |
|
"self": 5.180274127194934, |
|
"children": { |
|
"env_step": { |
|
"total": 4772.939104372194, |
|
"count": 192507, |
|
"self": 4390.172587254402, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 379.5830282929637, |
|
"count": 192507, |
|
"self": 15.347926996098977, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 364.23510129686474, |
|
"count": 187549, |
|
"self": 121.69350056174335, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 242.5416007351214, |
|
"count": 187549, |
|
"self": 242.5416007351214 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 3.1834888248286006, |
|
"count": 192507, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 7391.3437224265335, |
|
"count": 192507, |
|
"is_parallel": true, |
|
"self": 3360.819595076673, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0019106769996142248, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006517159990835353, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012589610005306895, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012589610005306895 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04981924700041418, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005316970000421861, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004576800001814263, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004576800001814263 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04700930600029096, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04700930600029096 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0018205639998996048, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004515860009632888, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001368977998936316, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001368977998936316 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 4030.5241273498605, |
|
"count": 192506, |
|
"is_parallel": true, |
|
"self": 93.57510296254623, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 77.95089503732379, |
|
"count": 192506, |
|
"is_parallel": true, |
|
"self": 77.95089503732379 |
|
}, |
|
"communicator.exchange": { |
|
"total": 3511.6009194647468, |
|
"count": 192506, |
|
"is_parallel": true, |
|
"self": 3511.6009194647468 |
|
}, |
|
"steps_from_proto": { |
|
"total": 347.3972098852437, |
|
"count": 192506, |
|
"is_parallel": true, |
|
"self": 78.90584047933771, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 268.49136940590597, |
|
"count": 1540048, |
|
"is_parallel": true, |
|
"self": 268.49136940590597 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 2617.4591947805957, |
|
"count": 192507, |
|
"self": 9.635674524552996, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 479.09892203501477, |
|
"count": 192507, |
|
"self": 478.4984932260122, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.6004288090025511, |
|
"count": 6, |
|
"self": 0.6004288090025511 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 2128.724598221028, |
|
"count": 1391, |
|
"self": 996.1768557010346, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 1132.5477425199933, |
|
"count": 56690, |
|
"self": 1132.5477425199933 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.919986041495577e-07, |
|
"count": 1, |
|
"self": 9.919986041495577e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.11477619799916283, |
|
"count": 1, |
|
"self": 0.0014028049990884028, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11337339300007443, |
|
"count": 1, |
|
"self": 0.11337339300007443 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |