{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5214080214500427, "min": 0.5214080214500427, "max": 1.5059053897857666, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15834.1181640625, "min": 15757.83203125, "max": 45683.14453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989965.0, "min": 29952.0, "max": 989965.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989965.0, "min": 29952.0, "max": 989965.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3382013440132141, "min": -0.19731155037879944, "max": 0.3382013440132141, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 90.29975891113281, "min": -46.76283645629883, "max": 90.29975891113281, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.08439874649047852, "min": -0.08439874649047852, "max": 0.25596997141838074, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -22.534465789794922, "min": -22.534465789794922, "max": 60.664886474609375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06847886762365565, "min": 0.06631287301561849, "max": 0.07260437941494827, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9587041467311792, "min": 0.48263285166392267, "max": 1.089065691224224, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.02323580888104126, "min": 0.00010184726740740536, "max": 0.02323580888104126, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.32530132433457765, "min": 0.0012221672088888642, "max": 0.32530132433457765, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.37178325705714e-06, "min": 7.37178325705714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010320496559879996, "min": 0.00010320496559879996, "max": 0.0033741613752795996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245722857142857, "min": 0.10245722857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344012, "min": 1.3691136000000002, "max": 2.4247204, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025547713428571427, "min": 0.00025547713428571427, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00357667988, "min": 0.00357667988, "max": 0.11248956796000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007499634753912687, "min": 0.007309727370738983, "max": 0.2847394645214081, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10499488562345505, "min": 0.10233618319034576, "max": 1.9931762218475342, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 484.57377049180326, "min": 484.57377049180326, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29559.0, "min": 15984.0, "max": 33028.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3842393236814952, "min": -1.0000000521540642, "max": 1.3842393236814952, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 84.43859874457121, "min": -32.000001668930054, "max": 84.43859874457121, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3842393236814952, "min": -1.0000000521540642, "max": 1.3842393236814952, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 84.43859874457121, "min": -32.000001668930054, "max": 84.43859874457121, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03876756464452511, "min": 0.03876756464452511, "max": 7.351232434622943, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.364821443316032, "min": 2.253193692100467, "max": 117.6197189539671, "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": "1697835237", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697838559" }, "total": 3321.7564754640007, "count": 1, "self": 0.602519131000463, "children": { "run_training.setup": { "total": 0.08263123999995514, "count": 1, "self": 0.08263123999995514 }, "TrainerController.start_learning": { "total": 3321.0713250930003, "count": 1, "self": 1.906674042073064, "children": { "TrainerController._reset_env": { "total": 1.9261367609999525, "count": 1, "self": 1.9261367609999525 }, "TrainerController.advance": { "total": 3317.156265854927, "count": 63378, "self": 2.1056538367906796, "children": { "env_step": { "total": 1763.1793080940633, "count": 63378, "self": 1624.8278282191357, "children": { "SubprocessEnvManager._take_step": { "total": 137.16137939189684, "count": 63378, "self": 5.811149257875741, "children": { "TorchPolicy.evaluate": { "total": 131.3502301340211, "count": 62569, "self": 131.3502301340211 } } }, "workers": { "total": 1.1901004830308466, "count": 63378, "self": 0.0, "children": { "worker_root": { "total": 3316.432443354893, "count": 63378, "is_parallel": true, "self": 1833.4598778098768, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021248109999305598, "count": 1, "is_parallel": true, "self": 0.0007026319997294195, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014221790002011403, "count": 8, "is_parallel": true, "self": 0.0014221790002011403 } } }, "UnityEnvironment.step": { "total": 0.059152579999818045, "count": 1, "is_parallel": true, "self": 0.0006335689997740701, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000472637000029863, "count": 1, "is_parallel": true, "self": 0.000472637000029863 }, "communicator.exchange": { "total": 0.056071234000000914, "count": 1, "is_parallel": true, "self": 0.056071234000000914 }, "steps_from_proto": { "total": 0.001975140000013198, "count": 1, "is_parallel": true, "self": 0.00041258199985350075, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015625580001596973, "count": 8, "is_parallel": true, "self": 0.0015625580001596973 } } } } } } }, "UnityEnvironment.step": { "total": 1482.9725655450163, "count": 63377, "is_parallel": true, "self": 40.36254056008511, "children": { "UnityEnvironment._generate_step_input": { "total": 22.507662612962577, "count": 63377, "is_parallel": true, "self": 22.507662612962577 }, "communicator.exchange": { "total": 1305.6388719569472, "count": 63377, "is_parallel": true, "self": 1305.6388719569472 }, "steps_from_proto": { "total": 114.4634904150214, "count": 63377, "is_parallel": true, "self": 24.314853736955683, "children": { "_process_rank_one_or_two_observation": { "total": 90.14863667806571, "count": 507016, "is_parallel": true, "self": 90.14863667806571 } } } } } } } } } } }, "trainer_advance": { "total": 1551.8713039240731, "count": 63378, "self": 3.607950509088141, "children": { "process_trajectory": { "total": 142.83420135298388, "count": 63378, "self": 142.6742737069842, "children": { "RLTrainer._checkpoint": { "total": 0.15992764599968723, "count": 2, "self": 0.15992764599968723 } } }, "_update_policy": { "total": 1405.429152062001, "count": 441, "self": 567.2396871720191, "children": { "TorchPPOOptimizer.update": { "total": 838.189464889982, "count": 38100, "self": 838.189464889982 } } } } } } }, "trainer_threads": { "total": 1.0720004866016097e-06, "count": 1, "self": 1.0720004866016097e-06 }, "TrainerController._save_models": { "total": 0.08224736299962387, "count": 1, "self": 0.0016013269996619783, "children": { "RLTrainer._checkpoint": { "total": 0.0806460359999619, "count": 1, "self": 0.0806460359999619 } } } } } } }