{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4808414876461029, "min": 0.45646536350250244, "max": 1.4761430025100708, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14525.259765625, "min": 13642.8369140625, "max": 44780.2734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.41117236018180847, "min": -0.1260172724723816, "max": 0.4495900273323059, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 108.54949951171875, "min": -30.370162963867188, "max": 121.83889770507812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025955229997634888, "min": 0.001035523833706975, "max": 0.307271271944046, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.8521809577941895, "min": 0.2692362070083618, "max": 73.74510192871094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06972378771923318, "min": 0.06514819621779247, "max": 0.07369894572346905, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9761330280692645, "min": 0.48059853971798655, "max": 1.0672664935021505, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010373268114048345, "min": 0.0001120277094408344, "max": 0.013814569378143335, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14522575359667683, "min": 0.001456360222730847, "max": 0.20619688992398247, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.424154668171426e-06, "min": 7.424154668171426e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010393816535439997, "min": 0.00010393816535439997, "max": 0.0031400270533243997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247468571428572, "min": 0.10247468571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346456, "min": 1.3691136000000002, "max": 2.3466756000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002572211028571428, "min": 0.0002572211028571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036010954399999994, "min": 0.0036010954399999994, "max": 0.10469289243999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009374582208693027, "min": 0.009374582208693027, "max": 0.4946654140949249, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13124415278434753, "min": 0.13124415278434753, "max": 3.462657928466797, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 449.4153846153846, "min": 388.9078947368421, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29212.0, "min": 15984.0, "max": 33324.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4274553592388446, "min": -1.0000000521540642, "max": 1.5058026062814813, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 92.7845983505249, "min": -32.000001668930054, "max": 114.44099807739258, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4274553592388446, "min": -1.0000000521540642, "max": 1.5058026062814813, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 92.7845983505249, "min": -32.000001668930054, "max": 114.44099807739258, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04350496525741899, "min": 0.040064290778613405, "max": 11.339918397367, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.827822741732234, "min": 2.827822741732234, "max": 181.438694357872, "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": "1690548181", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "0.31.0.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": "1690550179" }, "total": 1997.1754200600003, "count": 1, "self": 0.376533362000373, "children": { "run_training.setup": { "total": 0.03642111199997089, "count": 1, "self": 0.03642111199997089 }, "TrainerController.start_learning": { "total": 1996.762465586, "count": 1, "self": 1.8417457710179406, "children": { "TrainerController._reset_env": { "total": 4.610064933000103, "count": 1, "self": 4.610064933000103 }, "TrainerController.advance": { "total": 1990.206255852982, "count": 63469, "self": 1.7728782128874627, "children": { "env_step": { "total": 1337.9766422440039, "count": 63469, "self": 1207.4637519479638, "children": { "SubprocessEnvManager._take_step": { "total": 129.4123704990352, "count": 63469, "self": 5.3272204789532225, "children": { "TorchPolicy.evaluate": { "total": 124.08515002008198, "count": 62559, "self": 124.08515002008198 } } }, "workers": { "total": 1.1005197970048357, "count": 63469, "self": 0.0, "children": { "worker_root": { "total": 1993.7353670329908, "count": 63469, "is_parallel": true, "self": 904.2853400540353, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021563249997598177, "count": 1, "is_parallel": true, "self": 0.0006389270001818659, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015173979995779519, "count": 8, "is_parallel": true, "self": 0.0015173979995779519 } } }, "UnityEnvironment.step": { "total": 0.052196651000031125, "count": 1, "is_parallel": true, "self": 0.0006926920000296377, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005477709996739577, "count": 1, "is_parallel": true, "self": 0.0005477709996739577 }, "communicator.exchange": { "total": 0.04886110600000393, "count": 1, "is_parallel": true, "self": 0.04886110600000393 }, "steps_from_proto": { "total": 0.0020950820003236004, "count": 1, "is_parallel": true, "self": 0.00041708700018716627, "children": { "_process_rank_one_or_two_observation": { "total": 0.001677995000136434, "count": 8, "is_parallel": true, "self": 0.001677995000136434 } } } } } } }, "UnityEnvironment.step": { "total": 1089.4500269789555, "count": 63468, "is_parallel": true, "self": 28.919261706989346, "children": { "UnityEnvironment._generate_step_input": { "total": 19.919393866924565, "count": 63468, "is_parallel": true, "self": 19.919393866924565 }, "communicator.exchange": { "total": 958.6525405869716, "count": 63468, "is_parallel": true, "self": 958.6525405869716 }, "steps_from_proto": { "total": 81.95883081807006, "count": 63468, "is_parallel": true, "self": 17.70434792986498, "children": { "_process_rank_one_or_two_observation": { "total": 64.25448288820508, "count": 507744, "is_parallel": true, "self": 64.25448288820508 } } } } } } } } } } }, "trainer_advance": { "total": 650.4567353960906, "count": 63469, "self": 3.028257084075449, "children": { "process_trajectory": { "total": 108.0495058720162, "count": 63469, "self": 107.81499983501635, "children": { "RLTrainer._checkpoint": { "total": 0.2345060369998464, "count": 2, "self": 0.2345060369998464 } } }, "_update_policy": { "total": 539.378972439999, "count": 435, "self": 340.66695357000526, "children": { "TorchPPOOptimizer.update": { "total": 198.7120188699937, "count": 22875, "self": 198.7120188699937 } } } } } } }, "trainer_threads": { "total": 9.920004231389612e-07, "count": 1, "self": 9.920004231389612e-07 }, "TrainerController._save_models": { "total": 0.10439803699955519, "count": 1, "self": 0.0014601409993701964, "children": { "RLTrainer._checkpoint": { "total": 0.10293789600018499, "count": 1, "self": 0.10293789600018499 } } } } } } }