|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3278147578239441, |
|
"min": 0.3278147578239441, |
|
"max": 1.4880177974700928, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 9787.2373046875, |
|
"min": 9787.2373046875, |
|
"max": 45140.5078125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989931.0, |
|
"min": 29924.0, |
|
"max": 989931.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989931.0, |
|
"min": 29924.0, |
|
"max": 989931.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5349764823913574, |
|
"min": -0.15306486189365387, |
|
"max": 0.5530892014503479, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 150.32839965820312, |
|
"min": -36.42943572998047, |
|
"max": 152.65261840820312, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.02129850722849369, |
|
"min": -0.006660452112555504, |
|
"max": 0.18710607290267944, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.984880447387695, |
|
"min": -1.8449451923370361, |
|
"max": 44.90545654296875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06855354905322505, |
|
"min": 0.0646914835598889, |
|
"max": 0.07305705788794198, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9597496867451507, |
|
"min": 0.5844564631035358, |
|
"max": 1.0148837436863687, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.017782458136068834, |
|
"min": 0.000240785437767003, |
|
"max": 0.017782458136068834, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.24895441390496367, |
|
"min": 0.002648639815437033, |
|
"max": 0.24895441390496367, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.452868944314288e-06, |
|
"min": 7.452868944314288e-06, |
|
"max": 0.0002947653392448875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010434016522040003, |
|
"min": 0.00010434016522040003, |
|
"max": 0.0035072465309179002, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10248425714285715, |
|
"min": 0.10248425714285715, |
|
"max": 0.1982551125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4347796000000002, |
|
"min": 1.4347796000000002, |
|
"max": 2.5690821, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002581772885714287, |
|
"min": 0.0002581772885714287, |
|
"max": 0.00982568573875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036144820400000016, |
|
"min": 0.0036144820400000016, |
|
"max": 0.11693130179000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.007111009210348129, |
|
"min": 0.006715416442602873, |
|
"max": 0.32559260725975037, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.09955412894487381, |
|
"min": 0.09401582926511765, |
|
"max": 2.604740858078003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 356.7816091954023, |
|
"min": 336.8735632183908, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31040.0, |
|
"min": 17362.0, |
|
"max": 32753.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.528245951338061, |
|
"min": -0.9999806972280625, |
|
"max": 1.564570438624783, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 132.9573977664113, |
|
"min": -31.998801663517952, |
|
"max": 137.6821985989809, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.528245951338061, |
|
"min": -0.9999806972280625, |
|
"max": 1.564570438624783, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 132.9573977664113, |
|
"min": -31.998801663517952, |
|
"max": 137.6821985989809, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.0259063337760109, |
|
"min": 0.024837524914956458, |
|
"max": 6.268548468347742, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.2538510385129484, |
|
"min": 2.0366770430264296, |
|
"max": 112.83387243025936, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1673817520", |
|
"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", |
|
"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": "1673819504" |
|
}, |
|
"total": 1983.256521368, |
|
"count": 1, |
|
"self": 0.42552568699989024, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10250232899988987, |
|
"count": 1, |
|
"self": 0.10250232899988987 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1982.7284933520002, |
|
"count": 1, |
|
"self": 1.1489415319872478, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.197206898000104, |
|
"count": 1, |
|
"self": 6.197206898000104 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1975.2840630390122, |
|
"count": 63716, |
|
"self": 1.241711115957287, |
|
"children": { |
|
"env_step": { |
|
"total": 1327.5383560330422, |
|
"count": 63716, |
|
"self": 1228.7284332509764, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 98.1200690130413, |
|
"count": 63716, |
|
"self": 4.069057999027564, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 94.05101101401374, |
|
"count": 62550, |
|
"self": 31.926627588959718, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 62.12438342505402, |
|
"count": 62550, |
|
"self": 62.12438342505402 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.6898537690244666, |
|
"count": 63716, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1978.6144047849793, |
|
"count": 63716, |
|
"is_parallel": true, |
|
"self": 843.6352793440315, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0016353290000097331, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005941180002082547, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0010412109998014785, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0010412109998014785 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.042799306000006254, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004961329998423025, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00043435100019451056, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00043435100019451056 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04033565200006706, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04033565200006706 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001533169999902384, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003821039999820641, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011510659999203199, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011510659999203199 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1134.9791254409479, |
|
"count": 63715, |
|
"is_parallel": true, |
|
"self": 27.09342444988829, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 21.83237721495584, |
|
"count": 63715, |
|
"is_parallel": true, |
|
"self": 21.83237721495584 |
|
}, |
|
"communicator.exchange": { |
|
"total": 989.1790496909957, |
|
"count": 63715, |
|
"is_parallel": true, |
|
"self": 989.1790496909957 |
|
}, |
|
"steps_from_proto": { |
|
"total": 96.87427408510803, |
|
"count": 63715, |
|
"is_parallel": true, |
|
"self": 21.113900835071036, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 75.76037325003699, |
|
"count": 509720, |
|
"is_parallel": true, |
|
"self": 75.76037325003699 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 646.5039958900127, |
|
"count": 63716, |
|
"self": 2.1146254729658267, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 139.5880277450501, |
|
"count": 63716, |
|
"self": 139.38327755205046, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20475019299965425, |
|
"count": 2, |
|
"self": 0.20475019299965425 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 504.80134267199674, |
|
"count": 450, |
|
"self": 193.77169609900034, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 311.0296465729964, |
|
"count": 22857, |
|
"self": 311.0296465729964 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.58000327955233e-07, |
|
"count": 1, |
|
"self": 9.58000327955233e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.0982809250003811, |
|
"count": 1, |
|
"self": 0.001481639000303403, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0967992860000777, |
|
"count": 1, |
|
"self": 0.0967992860000777 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |