{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2476072758436203, "min": 0.2337554693222046, "max": 1.2702431678771973, "count": 40 }, "Pyramids.Policy.Entropy.sum": { "value": 7499.529296875, "min": 7001.44384765625, "max": 38534.09765625, "count": 40 }, "Pyramids.Step.mean": { "value": 1199921.0, "min": 29894.0, "max": 1199921.0, "count": 40 }, "Pyramids.Step.sum": { "value": 1199921.0, "min": 29894.0, "max": 1199921.0, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7036041021347046, "min": -0.06775975972414017, "max": 0.7863226532936096, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 204.74879455566406, "min": -16.330102920532227, "max": 235.89678955078125, "count": 40 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06506524980068207, "min": 0.0421072393655777, "max": 2.2533106803894043, "count": 40 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 18.93398666381836, "min": 12.042670249938965, "max": 534.0346069335938, "count": 40 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0696806831748247, "min": 0.06472908190119112, "max": 0.07398471183651827, "count": 40 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9755295644475458, "min": 0.5868626603907406, "max": 1.109770677547774, "count": 40 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016687173121941408, "min": 0.0028481249398592946, "max": 0.18689419954422828, "count": 40 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23362042370717973, "min": 0.03501328066399442, "max": 1.4951535963538263, "count": 40 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.89518798735119e-06, "min": 3.89518798735119e-06, "max": 0.00029607662630779164, "count": 40 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.4532631822916664e-05, "min": 5.4532631822916664e-05, "max": 0.00372811290729575, "count": 40 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1012983630952381, "min": 0.1012983630952381, "max": 0.19869220833333334, "count": 40 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4181770833333334, "min": 1.4181770833333334, "max": 2.718699416666667, "count": 40 }, "Pyramids.Policy.Beta.mean": { "value": 0.00013970647321428573, "min": 0.00013970647321428573, "max": 0.0098693516125, "count": 40 }, "Pyramids.Policy.Beta.sum": { "value": 0.001955890625, "min": 0.001955890625, "max": 0.12428615457500002, "count": 40 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01315945852547884, "min": 0.012633035890758038, "max": 0.5814580917358398, "count": 40 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1842324137687683, "min": 0.17686250805854797, "max": 4.651664733886719, "count": 40 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 274.29464285714283, "min": 234.42741935483872, "max": 990.90625, "count": 40 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30721.0, "min": 16693.0, "max": 34777.0, "count": 40 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6721124813359762, "min": -0.9293625522404909, "max": 1.7655725682214383, "count": 40 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 187.27659790962934, "min": -29.73960167169571, "max": 218.93099845945835, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6721124813359762, "min": -0.9293625522404909, "max": 1.7655725682214383, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 187.27659790962934, "min": -29.73960167169571, "max": 218.93099845945835, "count": 40 }, "Pyramids.Policy.RndReward.mean": { "value": 0.18404392301662093, "min": 0.15454967123138974, "max": 54.585772822884955, "count": 40 }, "Pyramids.Policy.RndReward.sum": { "value": 20.612919377861544, "min": 19.164159232692327, "max": 927.9581379890442, "count": 40 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1712585086", "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", "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": "1712588098" }, "total": 3011.6977769079995, "count": 1, "self": 0.4887333269998635, "children": { "run_training.setup": { "total": 0.05468389499992554, "count": 1, "self": 0.05468389499992554 }, "TrainerController.start_learning": { "total": 3011.1543596859997, "count": 1, "self": 1.9802229880087907, "children": { "TrainerController._reset_env": { "total": 2.892571040999883, "count": 1, "self": 2.892571040999883 }, "TrainerController.advance": { "total": 3006.161340819992, "count": 77216, "self": 2.0227871468778176, "children": { "env_step": { "total": 2203.6504767719784, "count": 77216, "self": 2024.3599974550434, "children": { "SubprocessEnvManager._take_step": { "total": 178.06270893296505, "count": 77216, "self": 6.453453675830133, "children": { "TorchPolicy.evaluate": { "total": 171.60925525713492, "count": 75074, "self": 171.60925525713492 } } }, "workers": { "total": 1.2277703839699825, "count": 77216, "self": 0.0, "children": { "worker_root": { "total": 3004.0877300298885, "count": 77216, "is_parallel": true, "self": 1150.430262634898, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030147999996188446, "count": 1, "is_parallel": true, "self": 0.0007903569994596182, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022244430001592264, "count": 8, "is_parallel": true, "self": 0.0022244430001592264 } } }, "UnityEnvironment.step": { "total": 0.05313116299976173, "count": 1, "is_parallel": true, "self": 0.0007288060000973928, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005420160000539909, "count": 1, "is_parallel": true, "self": 0.0005420160000539909 }, "communicator.exchange": { "total": 0.04977342599977419, "count": 1, "is_parallel": true, "self": 0.04977342599977419 }, "steps_from_proto": { "total": 0.0020869149998361536, "count": 1, "is_parallel": true, "self": 0.0004662739997911558, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016206410000449978, "count": 8, "is_parallel": true, "self": 0.0016206410000449978 } } } } } } }, "UnityEnvironment.step": { "total": 1853.6574673949904, "count": 77215, "is_parallel": true, "self": 46.11770036478538, "children": { "UnityEnvironment._generate_step_input": { "total": 32.743071154068275, "count": 77215, "is_parallel": true, "self": 32.743071154068275 }, "communicator.exchange": { "total": 1634.6419912821166, "count": 77215, "is_parallel": true, "self": 1634.6419912821166 }, "steps_from_proto": { "total": 140.15470459402013, "count": 77215, "is_parallel": true, "self": 29.791825061835425, "children": { "_process_rank_one_or_two_observation": { "total": 110.3628795321847, "count": 617720, "is_parallel": true, "self": 110.3628795321847 } } } } } } } } } } }, "trainer_advance": { "total": 800.4880769011356, "count": 77216, "self": 3.7574374371592967, "children": { "process_trajectory": { "total": 169.58988170497378, "count": 77216, "self": 169.36569203997306, "children": { "RLTrainer._checkpoint": { "total": 0.22418966500072202, "count": 2, "self": 0.22418966500072202 } } }, "_update_policy": { "total": 627.1407577590026, "count": 550, "self": 369.9164689700242, "children": { "TorchPPOOptimizer.update": { "total": 257.22428878897836, "count": 27339, "self": 257.22428878897836 } } } } } } }, "trainer_threads": { "total": 1.3079998097964562e-06, "count": 1, "self": 1.3079998097964562e-06 }, "TrainerController._save_models": { "total": 0.12022352899930411, "count": 1, "self": 0.0015571309986626147, "children": { "RLTrainer._checkpoint": { "total": 0.1186663980006415, "count": 1, "self": 0.1186663980006415 } } } } } } }