{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3137513995170593, "min": 0.2869039475917816, "max": 1.602157711982727, "count": 236 }, "Pyramids.Policy.Entropy.sum": { "value": 3268.03466796875, "min": 2579.84033203125, "max": 25634.5234375, "count": 236 }, "Pyramids.Step.mean": { "value": 2359943.0, "min": 9656.0, "max": 2359943.0, "count": 236 }, "Pyramids.Step.sum": { "value": 2359943.0, "min": 9656.0, "max": 2359943.0, "count": 236 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7108887434005737, "min": -0.11550861597061157, "max": 0.7489367723464966, "count": 236 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 30.56821632385254, "min": -2.1946637630462646, "max": 36.7609748840332, "count": 236 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011286488734185696, "min": -0.09177713841199875, "max": 0.3759949207305908, "count": 236 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.48531901836395264, "min": -1.7437655925750732, "max": 7.519898414611816, "count": 236 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.04953947659505145, "min": 0.04103936346124707, "max": 0.06559274251965151, "count": 236 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.0990789531901029, "min": 0.04532025255927389, "max": 0.17413268685156397, "count": 236 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013870685773915337, "min": 0.0001758237912478459, "max": 0.020322077112117164, "count": 236 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.027741371547830674, "min": 0.0001758237912478459, "max": 0.056052702401454255, "count": 236 }, "Pyramids.Policy.LearningRate.mean": { "value": 6.450972849678333e-05, "min": 6.450972849678333e-05, "max": 0.00029918080027306664, "count": 236 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00012901945699356665, "min": 0.00012901945699356665, "max": 0.0008054863315045666, "count": 236 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12150321666666666, "min": 0.12150321666666666, "max": 0.19972693333333336, "count": 236 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.24300643333333333, "min": 0.18914756666666668, "max": 0.5684954333333333, "count": 236 }, "Pyramids.Policy.Beta.mean": { "value": 0.002158171345, "min": 0.002158171345, "max": 0.00997272064, "count": 236 }, "Pyramids.Policy.Beta.sum": { "value": 0.00431634269, "min": 0.00431634269, "max": 0.02685269379, "count": 236 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0087517024949193, "min": 0.00788116455078125, "max": 0.887866199016571, "count": 236 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0175034049898386, "min": 0.0157623291015625, "max": 0.887866199016571, "count": 236 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 265.38461538461536, "min": 199.64, "max": 999.0, "count": 233 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 10350.0, "min": 999.0, "max": 15984.0, "count": 233 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7422307424056225, "min": -1.0000000596046448, "max": 1.799679981470108, "count": 236 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 67.94699895381927, "min": -16.000000953674316, "max": 89.9839990735054, "count": 236 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7422307424056225, "min": -1.0000000596046448, "max": 1.799679981470108, "count": 236 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 67.94699895381927, "min": -16.000000953674316, "max": 89.9839990735054, "count": 236 }, "Pyramids.Policy.RndReward.mean": { "value": 0.023170538909303453, "min": 0.01913863663900305, "max": 11.338852478907658, "count": 236 }, "Pyramids.Policy.RndReward.sum": { "value": 0.9036510174628347, "min": 0.6428126245737076, "max": 147.40508222579956, "count": 236 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 236 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 236 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708894521", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708899642" }, "total": 5121.063279811, "count": 1, "self": 0.5806893689996286, "children": { "run_training.setup": { "total": 0.04869531500025914, "count": 1, "self": 0.04869531500025914 }, "TrainerController.start_learning": { "total": 5120.433895127, "count": 1, "self": 3.0514399051926375, "children": { "TrainerController._reset_env": { "total": 2.512414589999935, "count": 1, "self": 2.512414589999935 }, "TrainerController.advance": { "total": 5114.870038967807, "count": 153082, "self": 3.185298800975943, "children": { "env_step": { "total": 3942.8121294630373, "count": 153082, "self": 3637.8237524569386, "children": { "SubprocessEnvManager._take_step": { "total": 303.0628151972214, "count": 153082, "self": 10.899881569044737, "children": { "TorchPolicy.evaluate": { "total": 292.1629336281767, "count": 148268, "self": 292.1629336281767 } } }, "workers": { "total": 1.925561808877319, "count": 153082, "self": 0.0, "children": { "worker_root": { "total": 5107.091545389932, "count": 153082, "is_parallel": true, "self": 1747.1022461868743, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021746020001955912, "count": 1, "is_parallel": true, "self": 0.0006800889996156911, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014945130005799, "count": 8, "is_parallel": true, "self": 0.0014945130005799 } } }, "UnityEnvironment.step": { "total": 0.051919086999987485, "count": 1, "is_parallel": true, "self": 0.0006314569991445751, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000514745000145922, "count": 1, "is_parallel": true, "self": 0.000514745000145922 }, "communicator.exchange": { "total": 0.04898608700023033, "count": 1, "is_parallel": true, "self": 0.04898608700023033 }, "steps_from_proto": { "total": 0.0017867980004666606, "count": 1, "is_parallel": true, "self": 0.000379430999601027, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014073670008656336, "count": 8, "is_parallel": true, "self": 0.0014073670008656336 } } } } } } }, "UnityEnvironment.step": { "total": 3359.989299203058, "count": 153081, "is_parallel": true, "self": 82.08729729548031, "children": { "UnityEnvironment._generate_step_input": { "total": 56.47116115370682, "count": 153081, "is_parallel": true, "self": 56.47116115370682 }, "communicator.exchange": { "total": 2990.37006701228, "count": 153081, "is_parallel": true, "self": 2990.37006701228 }, "steps_from_proto": { "total": 231.06077374159122, "count": 153081, "is_parallel": true, "self": 45.47935210940341, "children": { "_process_rank_one_or_two_observation": { "total": 185.5814216321878, "count": 1224648, "is_parallel": true, "self": 185.5814216321878 } } } } } } } } } } }, "trainer_advance": { "total": 1168.8726107037937, "count": 153082, "self": 6.951279846911348, "children": { "process_trajectory": { "total": 256.3582355698745, "count": 153082, "self": 255.9915498828732, "children": { "RLTrainer._checkpoint": { "total": 0.3666856870013362, "count": 4, "self": 0.3666856870013362 } } }, "_update_policy": { "total": 905.5630952870079, "count": 517, "self": 633.440543862157, "children": { "TorchPPOOptimizer.update": { "total": 272.1225514248508, "count": 27420, "self": 272.1225514248508 } } } } } } }, "trainer_threads": { "total": 1.6640005924273282e-06, "count": 1, "self": 1.6640005924273282e-06 } } } } }