{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38770797848701477, "min": 0.38770797848701477, "max": 1.4168798923492432, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11476.15625, "min": 11476.15625, "max": 42982.46875, "count": 33 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5542789697647095, "min": -0.09142249077558517, "max": 0.6234325170516968, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.5352783203125, "min": -21.94139862060547, "max": 178.92514038085938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00035446215770207345, "min": -0.007656983565539122, "max": 0.33424562215805054, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.09818601608276367, "min": -1.9831587076187134, "max": 79.2162094116211, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06704141551745124, "min": 0.06561804856017713, "max": 0.07392955514648343, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9385798172443174, "min": 0.5175052450052543, "max": 1.106688599022306, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014005116018303117, "min": 0.00042267426784736, "max": 0.01640567868340036, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19607162425624364, "min": 0.00464941694632096, "max": 0.24608518025100543, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.417704670321426e-06, "min": 7.417704670321426e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010384786538449996, "min": 0.00010384786538449996, "max": 0.0033707266764245, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247253571428573, "min": 0.10247253571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346155000000003, "min": 1.3886848, "max": 2.4850838, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002570063178571428, "min": 0.0002570063178571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003598088449999999, "min": 0.003598088449999999, "max": 0.11237519245, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012054323218762875, "min": 0.012006421573460102, "max": 0.36746978759765625, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1687605232000351, "min": 0.16808989644050598, "max": 2.5722885131835938, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 325.9529411764706, "min": 305.58252427184465, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27706.0, "min": 15984.0, "max": 32809.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6269764505765016, "min": -1.0000000521540642, "max": 1.673601907892869, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 138.29299829900265, "min": -31.9992016851902, "max": 174.05459842085838, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6269764505765016, "min": -1.0000000521540642, "max": 1.673601907892869, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 138.29299829900265, "min": -31.9992016851902, "max": 174.05459842085838, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04113525220857221, "min": 0.040498769248537986, "max": 7.027661400847137, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.496496437728638, "min": 3.496496437728638, "max": 112.44258241355419, "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": "1696846165", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1696848528" }, "total": 2362.9998489650006, "count": 1, "self": 0.5266309430007823, "children": { "run_training.setup": { "total": 0.06593622600030358, "count": 1, "self": 0.06593622600030358 }, "TrainerController.start_learning": { "total": 2362.4072817959996, "count": 1, "self": 1.470492509110045, "children": { "TrainerController._reset_env": { "total": 3.5388306649992955, "count": 1, "self": 3.5388306649992955 }, "TrainerController.advance": { "total": 2357.32134132589, "count": 63954, "self": 1.557576957972742, "children": { "env_step": { "total": 1657.1284930509164, "count": 63954, "self": 1525.1915131866717, "children": { "SubprocessEnvManager._take_step": { "total": 131.049751092095, "count": 63954, "self": 4.872536700171622, "children": { "TorchPolicy.evaluate": { "total": 126.17721439192337, "count": 62551, "self": 126.17721439192337 } } }, "workers": { "total": 0.8872287721496832, "count": 63954, "self": 0.0, "children": { "worker_root": { "total": 2357.3703702998946, "count": 63954, "is_parallel": true, "self": 960.889539142705, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003071039000133169, "count": 1, "is_parallel": true, "self": 0.0008422849987255177, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022287540014076512, "count": 8, "is_parallel": true, "self": 0.0022287540014076512 } } }, "UnityEnvironment.step": { "total": 0.05449102600050537, "count": 1, "is_parallel": true, "self": 0.0006042310014890973, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005044949994044146, "count": 1, "is_parallel": true, "self": 0.0005044949994044146 }, "communicator.exchange": { "total": 0.05137585000011313, "count": 1, "is_parallel": true, "self": 0.05137585000011313 }, "steps_from_proto": { "total": 0.0020064499994987273, "count": 1, "is_parallel": true, "self": 0.00044831600007455563, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015581339994241716, "count": 8, "is_parallel": true, "self": 0.0015581339994241716 } } } } } } }, "UnityEnvironment.step": { "total": 1396.4808311571896, "count": 63953, "is_parallel": true, "self": 34.658636218367064, "children": { "UnityEnvironment._generate_step_input": { "total": 25.210013683021316, "count": 63953, "is_parallel": true, "self": 25.210013683021316 }, "communicator.exchange": { "total": 1224.8429846428953, "count": 63953, "is_parallel": true, "self": 1224.8429846428953 }, "steps_from_proto": { "total": 111.76919661290594, "count": 63953, "is_parallel": true, "self": 22.45127606488768, "children": { "_process_rank_one_or_two_observation": { "total": 89.31792054801826, "count": 511624, "is_parallel": true, "self": 89.31792054801826 } } } } } } } } } } }, "trainer_advance": { "total": 698.6352713170008, "count": 63954, "self": 2.7886010410711606, "children": { "process_trajectory": { "total": 128.96115022493177, "count": 63954, "self": 128.7807374719314, "children": { "RLTrainer._checkpoint": { "total": 0.1804127530003825, "count": 2, "self": 0.1804127530003825 } } }, "_update_policy": { "total": 566.8855200509979, "count": 451, "self": 363.7912151309547, "children": { "TorchPPOOptimizer.update": { "total": 203.09430492004321, "count": 22803, "self": 203.09430492004321 } } } } } } }, "trainer_threads": { "total": 8.779998097452335e-07, "count": 1, "self": 8.779998097452335e-07 }, "TrainerController._save_models": { "total": 0.07661641800041252, "count": 1, "self": 0.0013588380006694933, "children": { "RLTrainer._checkpoint": { "total": 0.07525757999974303, "count": 1, "self": 0.07525757999974303 } } } } } } }