{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3538750112056732, "min": 0.33448612689971924, "max": 1.0712776184082031, "count": 31 }, "Pyramids.Policy.Entropy.sum": { "value": 10627.57421875, "min": 9997.12109375, "max": 31846.94140625, "count": 31 }, "Pyramids.Step.mean": { "value": 989905.0, "min": 89950.0, "max": 989905.0, "count": 31 }, "Pyramids.Step.sum": { "value": 989905.0, "min": 89950.0, "max": 989905.0, "count": 31 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6283882856369019, "min": -0.11587610095739365, "max": 0.6283882856369019, "count": 31 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 177.83389282226562, "min": -28.15789222717285, "max": 177.83389282226562, "count": 31 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0026639180723577738, "min": -0.007845763117074966, "max": 0.20376406610012054, "count": 31 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.7538888454437256, "min": -2.1575849056243896, "max": 35.402835845947266, "count": 31 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06816985339849321, "min": 0.06527967888772054, "max": 0.07334278545541954, "count": 31 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.954377947578905, "min": 0.2745188019956307, "max": 1.055494234465775, "count": 31 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016618954330726448, "min": 0.0009558179017690031, "max": 0.017008144175633785, "count": 31 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2326653606301703, "min": 0.01242563272299704, "max": 0.238114018458873, "count": 31 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.415583242457148e-06, "min": 7.415583242457148e-06, "max": 0.0002744238085254, "count": 31 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010381816539440007, "min": 0.00010381816539440007, "max": 0.0033731266756244997, "count": 31 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247182857142857, "min": 0.10247182857142857, "max": 0.19147460000000002, "count": 31 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346056, "min": 0.7658984000000001, "max": 2.4859533000000003, "count": 31 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002569356742857144, "min": 0.0002569356742857144, "max": 0.00914831254, "count": 31 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035970994400000016, "min": 0.0035970994400000016, "max": 0.11245511245, "count": 31 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014459864236414433, "min": 0.013391665183007717, "max": 0.12223175168037415, "count": 31 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2024381011724472, "min": 0.1874833106994629, "max": 1.1016923189163208, "count": 31 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 291.3333333333333, "min": 291.3333333333333, "max": 992.5806451612904, "count": 31 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29716.0, "min": 1561.0, "max": 32853.0, "count": 31 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6498215519183992, "min": -0.9289226306061591, "max": 1.6498215519183992, "count": 31 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 168.2817982956767, "min": -30.36020164191723, "max": 168.2817982956767, "count": 31 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6498215519183992, "min": -0.9289226306061591, "max": 1.6498215519183992, "count": 31 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 168.2817982956767, "min": -30.36020164191723, "max": 168.2817982956767, "count": 31 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04335330408802667, "min": 0.04335330408802667, "max": 1.2097931280732155, "count": 31 }, "Pyramids.Policy.RndReward.sum": { "value": 4.42203701697872, "min": 2.419586256146431, "max": 34.01006507780403, "count": 31 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 31 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 31 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1736006135", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736008343" }, "total": 2208.127555623, "count": 1, "self": 0.4388481889996001, "children": { "run_training.setup": { "total": 0.06218209799999386, "count": 1, "self": 0.06218209799999386 }, "TrainerController.start_learning": { "total": 2207.626525336, "count": 1, "self": 1.5181110490511855, "children": { "TrainerController._reset_env": { "total": 2.1447343389999105, "count": 1, "self": 2.1447343389999105 }, "TrainerController.advance": { "total": 2203.8776390239486, "count": 59081, "self": 1.5060000039648003, "children": { "env_step": { "total": 1552.069996361015, "count": 59081, "self": 1399.4676290439916, "children": { "SubprocessEnvManager._take_step": { "total": 151.7048934650204, "count": 59081, "self": 4.6428610709809846, "children": { "TorchPolicy.evaluate": { "total": 147.06203239403942, "count": 57782, "self": 147.06203239403942 } } }, "workers": { "total": 0.8974738520031451, "count": 59081, "self": 0.0, "children": { "worker_root": { "total": 2202.2518161919597, "count": 59081, "is_parallel": true, "self": 921.7489779719983, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002351481000005151, "count": 1, "is_parallel": true, "self": 0.0008601120002822427, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014913689997229085, "count": 8, "is_parallel": true, "self": 0.0014913689997229085 } } }, "UnityEnvironment.step": { "total": 0.05060125600004994, "count": 1, "is_parallel": true, "self": 0.0006766489999563419, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004915350000374019, "count": 1, "is_parallel": true, "self": 0.0004915350000374019 }, "communicator.exchange": { "total": 0.04776621000007708, "count": 1, "is_parallel": true, "self": 0.04776621000007708 }, "steps_from_proto": { "total": 0.001666861999979119, "count": 1, "is_parallel": true, "self": 0.00036945799990917294, "children": { "_process_rank_one_or_two_observation": { "total": 0.001297404000069946, "count": 8, "is_parallel": true, "self": 0.001297404000069946 } } } } } } }, "UnityEnvironment.step": { "total": 1280.5028382199614, "count": 59080, "is_parallel": true, "self": 32.48094805983692, "children": { "UnityEnvironment._generate_step_input": { "total": 22.286250625053754, "count": 59080, "is_parallel": true, "self": 22.286250625053754 }, "communicator.exchange": { "total": 1130.4400036230186, "count": 59080, "is_parallel": true, "self": 1130.4400036230186 }, "steps_from_proto": { "total": 95.29563591205215, "count": 59080, "is_parallel": true, "self": 20.382119465936853, "children": { "_process_rank_one_or_two_observation": { "total": 74.9135164461153, "count": 472640, "is_parallel": true, "self": 74.9135164461153 } } } } } } } } } } }, "trainer_advance": { "total": 650.301642658969, "count": 59081, "self": 2.8784928489799313, "children": { "process_trajectory": { "total": 126.67862153398721, "count": 59081, "self": 126.46057347198723, "children": { "RLTrainer._checkpoint": { "total": 0.21804806199997984, "count": 2, "self": 0.21804806199997984 } } }, "_update_policy": { "total": 520.7445282760018, "count": 427, "self": 290.4083490800099, "children": { "TorchPPOOptimizer.update": { "total": 230.33617919599192, "count": 21048, "self": 230.33617919599192 } } } } } } }, "trainer_threads": { "total": 1.6140002117026597e-06, "count": 1, "self": 1.6140002117026597e-06 }, "TrainerController._save_models": { "total": 0.08603931000016019, "count": 1, "self": 0.003018744000200968, "children": { "RLTrainer._checkpoint": { "total": 0.08302056599995922, "count": 1, "self": 0.08302056599995922 } } } } } } }