{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4181099534034729, "min": 0.4181099534034729, "max": 1.5149829387664795, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12536.6083984375, "min": 12536.6083984375, "max": 45958.5234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2663339376449585, "min": -0.10260331630706787, "max": 0.44559338688850403, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 68.71415710449219, "min": -24.727399826049805, "max": 117.63665771484375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.09756793826818466, "min": -0.03498930111527443, "max": 0.26096993684768677, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 25.172527313232422, "min": -8.922271728515625, "max": 61.849876403808594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06844425049032599, "min": 0.06494964779917468, "max": 0.07402353658558748, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9582195068645638, "min": 0.4892747904155297, "max": 1.0658862349228, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011957374548703218, "min": 0.0005443592410085995, "max": 0.013725443249667802, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16740324368184506, "min": 0.007076670133111793, "max": 0.19215620549534923, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.282619001064289e-06, "min": 7.282619001064289e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010195666601490005, "min": 0.00010195666601490005, "max": 0.0036331204889599004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242750714285716, "min": 0.10242750714285716, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339851000000001, "min": 1.3886848, "max": 2.6110401000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025250796357142866, "min": 0.00025250796357142866, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035351114900000016, "min": 0.0035351114900000016, "max": 0.12112290599, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011283555068075657, "min": 0.011283555068075657, "max": 0.3951511085033417, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15796977281570435, "min": 0.15796977281570435, "max": 2.7660577297210693, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 545.3518518518518, "min": 453.40909090909093, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29449.0, "min": 15984.0, "max": 33123.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1611962018991417, "min": -1.0000000521540642, "max": 1.3344181463348144, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 61.54339870065451, "min": -30.74000172317028, "max": 88.07159765809774, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1611962018991417, "min": -1.0000000521540642, "max": 1.3344181463348144, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 61.54339870065451, "min": -30.74000172317028, "max": 88.07159765809774, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06319271496119294, "min": 0.05841310634842199, "max": 7.6876135896891356, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.349213892943226, "min": 3.349213892943226, "max": 123.00181743502617, "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": "1682495965", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1682498243" }, "total": 2277.742449114, "count": 1, "self": 0.4861601210000117, "children": { "run_training.setup": { "total": 0.17232554499997832, "count": 1, "self": 0.17232554499997832 }, "TrainerController.start_learning": { "total": 2277.083963448, "count": 1, "self": 1.6843214539667315, "children": { "TrainerController._reset_env": { "total": 4.744244991999949, "count": 1, "self": 4.744244991999949 }, "TrainerController.advance": { "total": 2270.561652773033, "count": 63488, "self": 1.7480010220333497, "children": { "env_step": { "total": 1623.4389054400071, "count": 63488, "self": 1501.0141843339209, "children": { "SubprocessEnvManager._take_step": { "total": 121.41560811105194, "count": 63488, "self": 5.30598055306541, "children": { "TorchPolicy.evaluate": { "total": 116.10962755798653, "count": 62557, "self": 116.10962755798653 } } }, "workers": { "total": 1.009112995034343, "count": 63488, "self": 0.0, "children": { "worker_root": { "total": 2271.046936921068, "count": 63488, "is_parallel": true, "self": 898.4567409451063, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0059565390000102525, "count": 1, "is_parallel": true, "self": 0.003807540999957837, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021489980000524156, "count": 8, "is_parallel": true, "self": 0.0021489980000524156 } } }, "UnityEnvironment.step": { "total": 0.04832424500000343, "count": 1, "is_parallel": true, "self": 0.0005474150000281952, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005200980000381605, "count": 1, "is_parallel": true, "self": 0.0005200980000381605 }, "communicator.exchange": { "total": 0.0455827809999505, "count": 1, "is_parallel": true, "self": 0.0455827809999505 }, "steps_from_proto": { "total": 0.0016739509999865732, "count": 1, "is_parallel": true, "self": 0.0003718760000879229, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013020749998986503, "count": 8, "is_parallel": true, "self": 0.0013020749998986503 } } } } } } }, "UnityEnvironment.step": { "total": 1372.590195975962, "count": 63487, "is_parallel": true, "self": 34.622340077979516, "children": { "UnityEnvironment._generate_step_input": { "total": 25.677291746017204, "count": 63487, "is_parallel": true, "self": 25.677291746017204 }, "communicator.exchange": { "total": 1208.0918588880236, "count": 63487, "is_parallel": true, "self": 1208.0918588880236 }, "steps_from_proto": { "total": 104.19870526394175, "count": 63487, "is_parallel": true, "self": 23.06646933482989, "children": { "_process_rank_one_or_two_observation": { "total": 81.13223592911186, "count": 507896, "is_parallel": true, "self": 81.13223592911186 } } } } } } } } } } }, "trainer_advance": { "total": 645.3747463109926, "count": 63488, "self": 3.0282433300051252, "children": { "process_trajectory": { "total": 115.83071146098501, "count": 63488, "self": 115.62044697098491, "children": { "RLTrainer._checkpoint": { "total": 0.2102644900000996, "count": 2, "self": 0.2102644900000996 } } }, "_update_policy": { "total": 526.5157915200024, "count": 451, "self": 338.41808778798895, "children": { "TorchPPOOptimizer.update": { "total": 188.09770373201343, "count": 22803, "self": 188.09770373201343 } } } } } } }, "trainer_threads": { "total": 9.619998309062794e-07, "count": 1, "self": 9.619998309062794e-07 }, "TrainerController._save_models": { "total": 0.09374326700026359, "count": 1, "self": 0.001396547000240389, "children": { "RLTrainer._checkpoint": { "total": 0.0923467200000232, "count": 1, "self": 0.0923467200000232 } } } } } } }