|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.1536029428243637, |
|
"min": 0.14417099952697754, |
|
"max": 1.4970263242721558, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 4566.30810546875, |
|
"min": 4337.65283203125, |
|
"max": 45413.7890625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999947.0, |
|
"min": 29893.0, |
|
"max": 2999947.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999947.0, |
|
"min": 29893.0, |
|
"max": 2999947.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7773569226264954, |
|
"min": -0.105669766664505, |
|
"max": 0.9022570252418518, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 230.09764099121094, |
|
"min": -25.36074447631836, |
|
"max": 280.6019287109375, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.017287544906139374, |
|
"min": -0.009122959338128567, |
|
"max": 0.2013472616672516, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.11711311340332, |
|
"min": -2.6912729740142822, |
|
"max": 47.71929931640625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06689306465171588, |
|
"min": 0.06287849501182301, |
|
"max": 0.07455888452734775, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0033959697757382, |
|
"min": 0.4926247085242575, |
|
"max": 1.0794476781156845, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01308863873127848, |
|
"min": 0.0007681622101325362, |
|
"max": 0.016381051575364028, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.19632958096917721, |
|
"min": 0.009986108731722971, |
|
"max": 0.2457157736304604, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.4678861774044414e-06, |
|
"min": 1.4678861774044414e-06, |
|
"max": 0.00029841181481510954, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.201829266106662e-05, |
|
"min": 2.201829266106662e-05, |
|
"max": 0.003969544176818633, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10048926222222222, |
|
"min": 0.10048926222222222, |
|
"max": 0.19947060476190479, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5073389333333334, |
|
"min": 1.3962942333333335, |
|
"max": 2.8124702333333333, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 5.8877295999999914e-05, |
|
"min": 5.8877295999999914e-05, |
|
"max": 0.009947113415714285, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008831594399999987, |
|
"min": 0.0008831594399999987, |
|
"max": 0.13232581853, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.005559311714023352, |
|
"min": 0.005559311714023352, |
|
"max": 0.33594951033592224, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.08338967710733414, |
|
"min": 0.07972016930580139, |
|
"max": 2.351646661758423, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 240.29661016949152, |
|
"min": 197.99319727891157, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28355.0, |
|
"min": 16564.0, |
|
"max": 32526.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7082470406879897, |
|
"min": -0.999962551984936, |
|
"max": 1.799571413982224, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 203.28139784187078, |
|
"min": -31.998801663517952, |
|
"max": 277.1339977532625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7082470406879897, |
|
"min": -0.999962551984936, |
|
"max": 1.799571413982224, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 203.28139784187078, |
|
"min": -31.998801663517952, |
|
"max": 277.1339977532625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.014043053342596855, |
|
"min": 0.012422098022903406, |
|
"max": 6.334497824311256, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 1.6711233477690257, |
|
"min": 1.6711233477690257, |
|
"max": 107.68646301329136, |
|
"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": "1711523684", |
|
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", |
|
"command_line_arguments": "/home/node/WORK/WORKSPACE/ENVS/miscs/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", |
|
"mlagents_version": "1.1.0.dev0", |
|
"mlagents_envs_version": "1.1.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "2.2.1+cu121", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1711528266" |
|
}, |
|
"total": 4582.020049521, |
|
"count": 1, |
|
"self": 0.37061564800023916, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.022726857999941785, |
|
"count": 1, |
|
"self": 0.022726857999941785 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 4581.626707015, |
|
"count": 1, |
|
"self": 3.9419249230022615, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 2.05221949099996, |
|
"count": 1, |
|
"self": 2.05221949099996 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 4575.563441892998, |
|
"count": 195547, |
|
"self": 3.830409460185365, |
|
"children": { |
|
"env_step": { |
|
"total": 2856.3704914769683, |
|
"count": 195547, |
|
"self": 2412.504329834229, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 441.25603319179413, |
|
"count": 195547, |
|
"self": 11.307666733717724, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 429.9483664580764, |
|
"count": 187558, |
|
"self": 429.9483664580764 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.6101284509450124, |
|
"count": 195547, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 4576.378305785045, |
|
"count": 195547, |
|
"is_parallel": true, |
|
"self": 2430.811964703139, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0011908270000731136, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003349470005105104, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0008558799995626032, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0008558799995626032 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.026874547000034, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00026329900015298335, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0002055840000139142, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0002055840000139142 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.025487886999826515, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.025487886999826515 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0009177770000405872, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00021205999973972212, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.000705717000300865, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.000705717000300865 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 2145.566341081906, |
|
"count": 195546, |
|
"is_parallel": true, |
|
"self": 57.6902092295345, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 41.12992860235909, |
|
"count": 195546, |
|
"is_parallel": true, |
|
"self": 41.12992860235909 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1868.742386795, |
|
"count": 195546, |
|
"is_parallel": true, |
|
"self": 1868.742386795 |
|
}, |
|
"steps_from_proto": { |
|
"total": 178.0038164550126, |
|
"count": 195546, |
|
"is_parallel": true, |
|
"self": 40.80237823061884, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 137.20143822439377, |
|
"count": 1564368, |
|
"is_parallel": true, |
|
"self": 137.20143822439377 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1715.3625409558435, |
|
"count": 195547, |
|
"self": 7.055218625710495, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 343.18504393113653, |
|
"count": 195547, |
|
"self": 342.5013355471365, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.683708384000056, |
|
"count": 6, |
|
"self": 0.683708384000056 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1365.1222783989965, |
|
"count": 1401, |
|
"self": 750.260321691886, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 614.8619567071105, |
|
"count": 68436, |
|
"self": 614.8619567071105 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0379999366705306e-06, |
|
"count": 1, |
|
"self": 1.0379999366705306e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.06911966999996366, |
|
"count": 1, |
|
"self": 0.0010202869998465758, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.06809938300011709, |
|
"count": 1, |
|
"self": 0.06809938300011709 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |