{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4138519763946533, "min": 0.3812945485115051, "max": 1.4703525304794312, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12355.96484375, "min": 11448.685546875, "max": 44604.61328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989941.0, "min": 29935.0, "max": 989941.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989941.0, "min": 29935.0, "max": 989941.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4712086617946625, "min": -0.10479633510112762, "max": 0.48208585381507874, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 127.69754791259766, "min": -24.83673095703125, "max": 132.09152221679688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0022070547565817833, "min": -0.028307657688856125, "max": 0.5397907495498657, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.5981118679046631, "min": -7.473221778869629, "max": 127.93040466308594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06894058265256323, "min": 0.06314746864306651, "max": 0.07290178474833771, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9651681571358852, "min": 0.5103124932383639, "max": 1.0622252809698693, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01469826077146365, "min": 0.00035959729742020367, "max": 0.021611026998027517, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2057756508004911, "min": 0.003955570271622241, "max": 0.20701315502810758, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.377633255107145e-06, "min": 7.377633255107145e-06, "max": 0.0002952336444459286, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010328686557150003, "min": 0.00010328686557150003, "max": 0.0035071028309657994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245917857142858, "min": 0.10245917857142858, "max": 0.19841121428571426, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344285, "min": 1.3888785, "max": 2.5690342, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002556719392857143, "min": 0.0002556719392857143, "max": 0.009841280307142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003579407150000001, "min": 0.003579407150000001, "max": 0.11692651658, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012044703587889671, "min": 0.012044703587889671, "max": 0.5879420042037964, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1686258465051651, "min": 0.1686258465051651, "max": 4.115593910217285, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 404.0133333333333, "min": 400.22972972972974, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30301.0, "min": 16734.0, "max": 33236.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4359519854187965, "min": -0.9999677942645165, "max": 1.5186594361187638, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 107.69639890640974, "min": -30.999001622200012, "max": 112.38079827278852, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4359519854187965, "min": -0.9999677942645165, "max": 1.5186594361187638, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 107.69639890640974, "min": -30.999001622200012, "max": 112.38079827278852, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0507132926544485, "min": 0.0507132926544485, "max": 11.913546909304227, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8034969490836374, "min": 3.445794581217342, "max": 202.53029745817184, "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": "1683160661", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "1683162873" }, "total": 2211.989206421, "count": 1, "self": 0.54561238199949, "children": { "run_training.setup": { "total": 0.05845111899998301, "count": 1, "self": 0.05845111899998301 }, "TrainerController.start_learning": { "total": 2211.3851429200004, "count": 1, "self": 1.3628680290721604, "children": { "TrainerController._reset_env": { "total": 3.9207027200000084, "count": 1, "self": 3.9207027200000084 }, "TrainerController.advance": { "total": 2205.991675693928, "count": 63652, "self": 1.433937643882473, "children": { "env_step": { "total": 1574.132112423082, "count": 63652, "self": 1463.6317080490628, "children": { "SubprocessEnvManager._take_step": { "total": 109.68685011094976, "count": 63652, "self": 4.886190178885272, "children": { "TorchPolicy.evaluate": { "total": 104.80065993206449, "count": 62558, "self": 104.80065993206449 } } }, "workers": { "total": 0.8135542630693635, "count": 63652, "self": 0.0, "children": { "worker_root": { "total": 2206.2379859579787, "count": 63652, "is_parallel": true, "self": 858.0656854670376, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016912280000269675, "count": 1, "is_parallel": true, "self": 0.00047362600025735446, "children": { "_process_rank_one_or_two_observation": { "total": 0.001217601999769613, "count": 8, "is_parallel": true, "self": 0.001217601999769613 } } }, "UnityEnvironment.step": { "total": 0.05178520000004028, "count": 1, "is_parallel": true, "self": 0.0005184849997021956, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048198800004684017, "count": 1, "is_parallel": true, "self": 0.00048198800004684017 }, "communicator.exchange": { "total": 0.04909257000008438, "count": 1, "is_parallel": true, "self": 0.04909257000008438 }, "steps_from_proto": { "total": 0.001692157000206862, "count": 1, "is_parallel": true, "self": 0.00035349399968254147, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013386630005243205, "count": 8, "is_parallel": true, "self": 0.0013386630005243205 } } } } } } }, "UnityEnvironment.step": { "total": 1348.172300490941, "count": 63651, "is_parallel": true, "self": 31.35869364489463, "children": { "UnityEnvironment._generate_step_input": { "total": 23.820554875059315, "count": 63651, "is_parallel": true, "self": 23.820554875059315 }, "communicator.exchange": { "total": 1192.2163464650196, "count": 63651, "is_parallel": true, "self": 1192.2163464650196 }, "steps_from_proto": { "total": 100.77670550596758, "count": 63651, "is_parallel": true, "self": 20.71778217890369, "children": { "_process_rank_one_or_two_observation": { "total": 80.0589233270639, "count": 509208, "is_parallel": true, "self": 80.0589233270639 } } } } } } } } } } }, "trainer_advance": { "total": 630.4256256269634, "count": 63652, "self": 2.520469835925951, "children": { "process_trajectory": { "total": 109.40068988803478, "count": 63652, "self": 109.13656169603473, "children": { "RLTrainer._checkpoint": { "total": 0.2641281920000438, "count": 2, "self": 0.2641281920000438 } } }, "_update_policy": { "total": 518.5044659030027, "count": 453, "self": 333.98100324501706, "children": { "TorchPPOOptimizer.update": { "total": 184.52346265798565, "count": 22806, "self": 184.52346265798565 } } } } } } }, "trainer_threads": { "total": 1.440000232832972e-06, "count": 1, "self": 1.440000232832972e-06 }, "TrainerController._save_models": { "total": 0.10989503700011483, "count": 1, "self": 0.0015170299998317205, "children": { "RLTrainer._checkpoint": { "total": 0.1083780070002831, "count": 1, "self": 0.1083780070002831 } } } } } } }