| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.3850148916244507, | |
| "min": 0.3736658990383148, | |
| "max": 1.403730034828186, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 11556.607421875, | |
| "min": 11078.4462890625, | |
| "max": 42583.5546875, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 989963.0, | |
| "min": 29915.0, | |
| "max": 989963.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 989963.0, | |
| "min": 29915.0, | |
| "max": 989963.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.5188890695571899, | |
| "min": -0.12454988062381744, | |
| "max": 0.5331054329872131, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 142.69448852539062, | |
| "min": -29.891971588134766, | |
| "max": 146.60398864746094, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.023866167291998863, | |
| "min": -0.0111561119556427, | |
| "max": 0.43092843890190125, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 6.563196182250977, | |
| "min": -3.0344624519348145, | |
| "max": 102.13004302978516, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.07123437206365536, | |
| "min": 0.06470598120081593, | |
| "max": 0.0735213648708951, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.997281208891175, | |
| "min": 0.5696150898927757, | |
| "max": 1.1028204730634266, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.01580614767472096, | |
| "min": 0.001137092577986113, | |
| "max": 0.01677967188264346, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.22128606744609344, | |
| "min": 0.015919296091805583, | |
| "max": 0.23491540635700847, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.42351181124286e-06, | |
| "min": 7.42351181124286e-06, | |
| "max": 0.0002948428892190375, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.00010392916535740004, | |
| "min": 0.00010392916535740004, | |
| "max": 0.003724224658591799, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10247447142857144, | |
| "min": 0.10247447142857144, | |
| "max": 0.1982809625, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4346426, | |
| "min": 1.4346426, | |
| "max": 2.617613000000001, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.0002571996957142858, | |
| "min": 0.0002571996957142858, | |
| "max": 0.00982826815375, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0036007957400000018, | |
| "min": 0.0036007957400000018, | |
| "max": 0.12414667918000002, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.014671503566205502, | |
| "min": 0.014671503566205502, | |
| "max": 0.5129152536392212, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.20540104806423187, | |
| "min": 0.20540104806423187, | |
| "max": 4.1033220291137695, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 348.26506024096386, | |
| "min": 348.26506024096386, | |
| "max": 995.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 28906.0, | |
| "min": 17097.0, | |
| "max": 32424.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.5553204632667175, | |
| "min": -0.9333813029807061, | |
| "max": 1.6233633898380326, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 129.09159845113754, | |
| "min": -29.868201695382595, | |
| "max": 133.73779855668545, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.5553204632667175, | |
| "min": -0.9333813029807061, | |
| "max": 1.6233633898380326, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 129.09159845113754, | |
| "min": -29.868201695382595, | |
| "max": 133.73779855668545, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.05288865482638007, | |
| "min": 0.05288865482638007, | |
| "max": 10.20352097021209, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 4.389758350589545, | |
| "min": 4.389758350589545, | |
| "max": 183.6633774638176, | |
| "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": "1680954774", | |
| "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", | |
| "command_line_arguments": "/home/sicong/Data/Projects/HuggingFace_DeepReinforcementLearning/venv_shared/bin/mlagents-learn ./ml-agents/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": "1680956032" | |
| }, | |
| "total": 1258.4368059220142, | |
| "count": 1, | |
| "self": 0.21992897504242137, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.019899851991795003, | |
| "count": 1, | |
| "self": 0.019899851991795003 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 1258.19697709498, | |
| "count": 1, | |
| "self": 1.0607770374044776, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 2.846834211028181, | |
| "count": 1, | |
| "self": 2.846834211028181 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 1254.2096045695362, | |
| "count": 63903, | |
| "self": 0.9535994690959342, | |
| "children": { | |
| "env_step": { | |
| "total": 793.6582737493445, | |
| "count": 63903, | |
| "self": 684.1445936444798, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 108.85136416344903, | |
| "count": 63903, | |
| "self": 2.6127780139795505, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 106.23858614946948, | |
| "count": 62560, | |
| "self": 106.23858614946948 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.6623159414157271, | |
| "count": 63903, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 1256.6302440160653, | |
| "count": 63903, | |
| "is_parallel": true, | |
| "self": 637.8741833117092, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0011611069785431027, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00037755194352939725, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0007835550350137055, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0007835550350137055 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.02313803305150941, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0002915430814027786, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0002708919928409159, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0002708919928409159 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.021812483959365636, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.021812483959365636 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0007631140179000795, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00017198000568896532, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0005911340122111142, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0005911340122111142 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 618.7560607043561, | |
| "count": 63902, | |
| "is_parallel": true, | |
| "self": 20.38584548048675, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 14.031576734676491, | |
| "count": 63902, | |
| "is_parallel": true, | |
| "self": 14.031576734676491 | |
| }, | |
| "communicator.exchange": { | |
| "total": 535.8076451613451, | |
| "count": 63902, | |
| "is_parallel": true, | |
| "self": 535.8076451613451 | |
| }, | |
| "steps_from_proto": { | |
| "total": 48.53099332784768, | |
| "count": 63902, | |
| "is_parallel": true, | |
| "self": 9.902067869785242, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 38.62892545806244, | |
| "count": 511216, | |
| "is_parallel": true, | |
| "self": 38.62892545806244 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 459.5977313510957, | |
| "count": 63903, | |
| "self": 1.9296662296401337, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 81.51492056960706, | |
| "count": 63903, | |
| "self": 81.37069327553036, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.14422729407669976, | |
| "count": 2, | |
| "self": 0.14422729407669976 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 376.1531445518485, | |
| "count": 462, | |
| "self": 226.39872767933412, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 149.7544168725144, | |
| "count": 22758, | |
| "self": 149.7544168725144 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 6.100162863731384e-07, | |
| "count": 1, | |
| "self": 6.100162863731384e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.07976066699484363, | |
| "count": 1, | |
| "self": 0.0008779889903962612, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.07888267800444737, | |
| "count": 1, | |
| "self": 0.07888267800444737 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |