{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47613778710365295, "min": 0.47613778710365295, "max": 1.3980376720428467, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14421.26171875, "min": 14421.26171875, "max": 42410.87109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989934.0, "min": 29952.0, "max": 989934.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989934.0, "min": 29952.0, "max": 989934.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4990027844905853, "min": -0.10876626521348953, "max": 0.5650585293769836, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 135.728759765625, "min": -26.212669372558594, "max": 158.7814483642578, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.1437314748764038, "min": -0.1437314748764038, "max": 0.39419472217559814, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -39.0949592590332, "min": -39.0949592590332, "max": 93.42414855957031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07003421247645748, "min": 0.06473597233915436, "max": 0.07241351842059797, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9804789746704047, "min": 0.5008768984886025, "max": 1.0766200213168071, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.021635045607191778, "min": 0.00010482312769835671, "max": 0.021635045607191778, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3028906385006849, "min": 0.0013627006600786373, "max": 0.3028906385006849, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.676561726892854e-06, "min": 7.676561726892854e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010747186417649996, "min": 0.00010747186417649996, "max": 0.0035080271306576994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255882142857145, "min": 0.10255882142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358235000000004, "min": 1.3886848, "max": 2.5693422999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026562626071428564, "min": 0.00026562626071428564, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003718767649999999, "min": 0.003718767649999999, "max": 0.11695729577000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012441134080290794, "min": 0.012441134080290794, "max": 0.3748336136341095, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17417587339878082, "min": 0.17417587339878082, "max": 2.623835325241089, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 372.2560975609756, "min": 327.7717391304348, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30525.0, "min": 15984.0, "max": 32509.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.530156071138818, "min": -1.0000000521540642, "max": 1.672228242068187, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 125.47279783338308, "min": -31.998401656746864, "max": 153.8449982702732, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.530156071138818, "min": -1.0000000521540642, "max": 1.672228242068187, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 125.47279783338308, "min": -31.998401656746864, "max": 153.8449982702732, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.047866029094532164, "min": 0.04403932072486698, "max": 7.197150720283389, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9250143857516377, "min": 3.9250143857516377, "max": 115.15441152453423, "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": "1701731383", "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=PyramidsTraining --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701733756" }, "total": 2372.4121972450002, "count": 1, "self": 0.48593736000020726, "children": { "run_training.setup": { "total": 0.0570763519999673, "count": 1, "self": 0.0570763519999673 }, "TrainerController.start_learning": { "total": 2371.869183533, "count": 1, "self": 1.4562043179539614, "children": { "TrainerController._reset_env": { "total": 2.984032180999975, "count": 1, "self": 2.984032180999975 }, "TrainerController.advance": { "total": 2367.3491231290463, "count": 63655, "self": 1.5260773620052532, "children": { "env_step": { "total": 1705.2147420820381, "count": 63655, "self": 1563.360672762085, "children": { "SubprocessEnvManager._take_step": { "total": 140.93682568901568, "count": 63655, "self": 5.173785515969257, "children": { "TorchPolicy.evaluate": { "total": 135.76304017304642, "count": 62560, "self": 135.76304017304642 } } }, "workers": { "total": 0.9172436309374916, "count": 63655, "self": 0.0, "children": { "worker_root": { "total": 2366.588477659012, "count": 63655, "is_parallel": true, "self": 935.2199131990028, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001973141000007672, "count": 1, "is_parallel": true, "self": 0.0006929919998128753, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012801490001947968, "count": 8, "is_parallel": true, "self": 0.0012801490001947968 } } }, "UnityEnvironment.step": { "total": 0.0895552229999339, "count": 1, "is_parallel": true, "self": 0.0005975999997644976, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005313910000950273, "count": 1, "is_parallel": true, "self": 0.0005313910000950273 }, "communicator.exchange": { "total": 0.08667235400002937, "count": 1, "is_parallel": true, "self": 0.08667235400002937 }, "steps_from_proto": { "total": 0.001753878000045006, "count": 1, "is_parallel": true, "self": 0.0003618880004978564, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013919899995471496, "count": 8, "is_parallel": true, "self": 0.0013919899995471496 } } } } } } }, "UnityEnvironment.step": { "total": 1431.368564460009, "count": 63654, "is_parallel": true, "self": 35.768255914033944, "children": { "UnityEnvironment._generate_step_input": { "total": 26.49456458196505, "count": 63654, "is_parallel": true, "self": 26.49456458196505 }, "communicator.exchange": { "total": 1262.398608902031, "count": 63654, "is_parallel": true, "self": 1262.398608902031 }, "steps_from_proto": { "total": 106.70713506197922, "count": 63654, "is_parallel": true, "self": 21.942467324918425, "children": { "_process_rank_one_or_two_observation": { "total": 84.76466773706079, "count": 509232, "is_parallel": true, "self": 84.76466773706079 } } } } } } } } } } }, "trainer_advance": { "total": 660.608303685003, "count": 63655, "self": 2.680369134957573, "children": { "process_trajectory": { "total": 136.10100892804053, "count": 63655, "self": 135.88093456304, "children": { "RLTrainer._checkpoint": { "total": 0.2200743650005279, "count": 2, "self": 0.2200743650005279 } } }, "_update_policy": { "total": 521.8269256220049, "count": 445, "self": 313.44141928802287, "children": { "TorchPPOOptimizer.update": { "total": 208.385506333982, "count": 22776, "self": 208.385506333982 } } } } } } }, "trainer_threads": { "total": 8.719998731976375e-07, "count": 1, "self": 8.719998731976375e-07 }, "TrainerController._save_models": { "total": 0.07982303300013882, "count": 1, "self": 0.0013153159998182673, "children": { "RLTrainer._checkpoint": { "total": 0.07850771700032055, "count": 1, "self": 0.07850771700032055 } } } } } } }