{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4500786066055298, "min": 0.4500786066055298, "max": 1.3810206651687622, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13646.3837890625, "min": 13646.3837890625, "max": 41894.64453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989897.0, "min": 29952.0, "max": 989897.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989897.0, "min": 29952.0, "max": 989897.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5151572227478027, "min": -0.12215037643909454, "max": 0.5151572227478027, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 141.153076171875, "min": -29.43824005126953, "max": 141.153076171875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014911537058651447, "min": -0.08371836692094803, "max": 0.2870444655418396, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.085761070251465, "min": -22.603960037231445, "max": 68.029541015625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06654959774220033, "min": 0.06521139639535008, "max": 0.07405010960327672, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.998243966133005, "min": 0.518350767222937, "max": 1.0574084003535829, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016245239312791728, "min": 0.0006387871787954819, "max": 0.01651614439065775, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24367858969187595, "min": 0.008943020503136747, "max": 0.24774216585986625, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.501277499606666e-06, "min": 7.501277499606666e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011251916249409999, "min": 0.00011251916249409999, "max": 0.0035092562302479996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250039333333334, "min": 0.10250039333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375059000000002, "min": 1.3886848, "max": 2.569752, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002597892939999999, "min": 0.0002597892939999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038968394099999993, "min": 0.0038968394099999993, "max": 0.11699822480000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012059287168085575, "min": 0.012059287168085575, "max": 0.4500819146633148, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1808893084526062, "min": 0.1732906550168991, "max": 3.150573492050171, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 375.679012345679, "min": 359.02666666666664, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30430.0, "min": 15984.0, "max": 34072.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5502320855488012, "min": -1.0000000521540642, "max": 1.614831568575219, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 125.5687989294529, "min": -29.043801717460155, "max": 125.5687989294529, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5502320855488012, "min": -1.0000000521540642, "max": 1.614831568575219, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 125.5687989294529, "min": -29.043801717460155, "max": 125.5687989294529, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04754898220481765, "min": 0.045640675541730354, "max": 8.708266717381775, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8514675585902296, "min": 3.468691341171507, "max": 139.3322674781084, "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": "1699248687", "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": "1699250861" }, "total": 2174.388396805, "count": 1, "self": 0.48688932599998225, "children": { "run_training.setup": { "total": 0.046325894000005974, "count": 1, "self": 0.046325894000005974 }, "TrainerController.start_learning": { "total": 2173.855181585, "count": 1, "self": 1.3854548140297993, "children": { "TrainerController._reset_env": { "total": 8.185841880999988, "count": 1, "self": 8.185841880999988 }, "TrainerController.advance": { "total": 2164.2073207759704, "count": 63731, "self": 1.432232740019117, "children": { "env_step": { "total": 1531.2334948979856, "count": 63731, "self": 1395.5651564980185, "children": { "SubprocessEnvManager._take_step": { "total": 134.81597599399024, "count": 63731, "self": 4.533397522004719, "children": { "TorchPolicy.evaluate": { "total": 130.28257847198552, "count": 62562, "self": 130.28257847198552 } } }, "workers": { "total": 0.8523624059767485, "count": 63731, "self": 0.0, "children": { "worker_root": { "total": 2169.277486908989, "count": 63731, "is_parallel": true, "self": 888.274935259944, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005169494999989865, "count": 1, "is_parallel": true, "self": 0.00377290900004823, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013965859999416352, "count": 8, "is_parallel": true, "self": 0.0013965859999416352 } } }, "UnityEnvironment.step": { "total": 0.07874841200001015, "count": 1, "is_parallel": true, "self": 0.0006436150000013185, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046620300000199677, "count": 1, "is_parallel": true, "self": 0.00046620300000199677 }, "communicator.exchange": { "total": 0.0756380250000177, "count": 1, "is_parallel": true, "self": 0.0756380250000177 }, "steps_from_proto": { "total": 0.0020005689999891274, "count": 1, "is_parallel": true, "self": 0.00038481799998635324, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016157510000027742, "count": 8, "is_parallel": true, "self": 0.0016157510000027742 } } } } } } }, "UnityEnvironment.step": { "total": 1281.002551649045, "count": 63730, "is_parallel": true, "self": 34.7033393480674, "children": { "UnityEnvironment._generate_step_input": { "total": 24.049048680973442, "count": 63730, "is_parallel": true, "self": 24.049048680973442 }, "communicator.exchange": { "total": 1125.2480859019906, "count": 63730, "is_parallel": true, "self": 1125.2480859019906 }, "steps_from_proto": { "total": 97.00207771801342, "count": 63730, "is_parallel": true, "self": 19.516403918053385, "children": { "_process_rank_one_or_two_observation": { "total": 77.48567379996004, "count": 509840, "is_parallel": true, "self": 77.48567379996004 } } } } } } } } } } }, "trainer_advance": { "total": 631.5415931379657, "count": 63731, "self": 2.655191508931466, "children": { "process_trajectory": { "total": 120.29493646303357, "count": 63731, "self": 120.07963205503395, "children": { "RLTrainer._checkpoint": { "total": 0.2153044079996107, "count": 2, "self": 0.2153044079996107 } } }, "_update_policy": { "total": 508.59146516600066, "count": 453, "self": 304.42848014801825, "children": { "TorchPPOOptimizer.update": { "total": 204.1629850179824, "count": 22785, "self": 204.1629850179824 } } } } } } }, "trainer_threads": { "total": 1.3270000636111945e-06, "count": 1, "self": 1.3270000636111945e-06 }, "TrainerController._save_models": { "total": 0.07656278700005714, "count": 1, "self": 0.0014383359998646483, "children": { "RLTrainer._checkpoint": { "total": 0.0751244510001925, "count": 1, "self": 0.0751244510001925 } } } } } } }