{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2836567461490631, "min": 0.2836567461490631, "max": 1.4694892168045044, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8432.5478515625, "min": 8432.5478515625, "max": 44578.42578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989996.0, "min": 29952.0, "max": 989996.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989996.0, "min": 29952.0, "max": 989996.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49994927644729614, "min": -0.1305467188358307, "max": 0.5332083106040955, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 137.48605346679688, "min": -31.46175765991211, "max": 148.23190307617188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.01603609137237072, "min": -0.01603609137237072, "max": 0.6299103498458862, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.4099249839782715, "min": -4.4099249839782715, "max": 149.28875732421875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07233204942825806, "min": 0.06281718738986307, "max": 0.07366803193513707, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0126486919956128, "min": 0.4947505360863964, "max": 1.0636879104228378, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017735935442033227, "min": 0.00046141909700384985, "max": 0.021521358250481716, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24830309618846516, "min": 0.005998448261050048, "max": 0.2542119495931319, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.370197543300007e-06, "min": 7.370197543300007e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010318276560620009, "min": 0.00010318276560620009, "max": 0.0035087885304038993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245669999999998, "min": 0.10245669999999998, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343937999999998, "min": 1.3886848, "max": 2.5695961000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002554243300000002, "min": 0.0002554243300000002, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035759406200000033, "min": 0.0035759406200000033, "max": 0.11698265039, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.017071325331926346, "min": 0.016508202999830246, "max": 0.7039014101028442, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23899856209754944, "min": 0.23899856209754944, "max": 4.927309989929199, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 341.0595238095238, "min": 336.0, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28649.0, "min": 15984.0, "max": 32758.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.587590455299332, "min": -1.0000000521540642, "max": 1.6278870386235855, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 133.3575982451439, "min": -30.99660161137581, "max": 142.74779879301786, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.587590455299332, "min": -1.0000000521540642, "max": 1.6278870386235855, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 133.3575982451439, "min": -30.99660161137581, "max": 142.74779879301786, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06399763829280605, "min": 0.061672155620496584, "max": 15.730707893148065, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.375801616595709, "min": 5.118788916501217, "max": 251.69132629036903, "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": "1693509408", "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": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1693511732" }, "total": 2323.430040903, "count": 1, "self": 0.5381145810006274, "children": { "run_training.setup": { "total": 0.03974262399992767, "count": 1, "self": 0.03974262399992767 }, "TrainerController.start_learning": { "total": 2322.852183698, "count": 1, "self": 1.438442913979543, "children": { "TrainerController._reset_env": { "total": 4.250111778000019, "count": 1, "self": 4.250111778000019 }, "TrainerController.advance": { "total": 2317.0679981280205, "count": 63860, "self": 1.44059738699616, "children": { "env_step": { "total": 1636.3489704890226, "count": 63860, "self": 1523.0756310509892, "children": { "SubprocessEnvManager._take_step": { "total": 112.39315418705041, "count": 63860, "self": 4.852765732069884, "children": { "TorchPolicy.evaluate": { "total": 107.54038845498053, "count": 62564, "self": 107.54038845498053 } } }, "workers": { "total": 0.8801852509830042, "count": 63860, "self": 0.0, "children": { "worker_root": { "total": 2317.3007173260658, "count": 63860, "is_parallel": true, "self": 911.8025160309294, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018380120000074385, "count": 1, "is_parallel": true, "self": 0.000559856000563741, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012781559994436975, "count": 8, "is_parallel": true, "self": 0.0012781559994436975 } } }, "UnityEnvironment.step": { "total": 0.053314542999942205, "count": 1, "is_parallel": true, "self": 0.0006273129999954108, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005255620001207717, "count": 1, "is_parallel": true, "self": 0.0005255620001207717 }, "communicator.exchange": { "total": 0.05012770999996974, "count": 1, "is_parallel": true, "self": 0.05012770999996974 }, "steps_from_proto": { "total": 0.002033957999856284, "count": 1, "is_parallel": true, "self": 0.00036881299979540927, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016651450000608747, "count": 8, "is_parallel": true, "self": 0.0016651450000608747 } } } } } } }, "UnityEnvironment.step": { "total": 1405.4982012951364, "count": 63859, "is_parallel": true, "self": 34.57477382917409, "children": { "UnityEnvironment._generate_step_input": { "total": 23.143688888997758, "count": 63859, "is_parallel": true, "self": 23.143688888997758 }, "communicator.exchange": { "total": 1240.7701623919672, "count": 63859, "is_parallel": true, "self": 1240.7701623919672 }, "steps_from_proto": { "total": 107.00957618499729, "count": 63859, "is_parallel": true, "self": 20.941761565002935, "children": { "_process_rank_one_or_two_observation": { "total": 86.06781461999435, "count": 510872, "is_parallel": true, "self": 86.06781461999435 } } } } } } } } } } }, "trainer_advance": { "total": 679.2784302520017, "count": 63860, "self": 2.701362380014416, "children": { "process_trajectory": { "total": 114.66758121898897, "count": 63860, "self": 114.46157129398875, "children": { "RLTrainer._checkpoint": { "total": 0.20600992500021675, "count": 2, "self": 0.20600992500021675 } } }, "_update_policy": { "total": 561.9094866529983, "count": 453, "self": 364.5136580320068, "children": { "TorchPPOOptimizer.update": { "total": 197.39582862099155, "count": 22803, "self": 197.39582862099155 } } } } } } }, "trainer_threads": { "total": 9.259997568733525e-07, "count": 1, "self": 9.259997568733525e-07 }, "TrainerController._save_models": { "total": 0.09562995200030855, "count": 1, "self": 0.001476261000334489, "children": { "RLTrainer._checkpoint": { "total": 0.09415369099997406, "count": 1, "self": 0.09415369099997406 } } } } } } }