{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.732119619846344, "min": 0.7186362743377686, "max": 1.4985047578811646, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 21705.8828125, "min": 21432.607421875, "max": 45458.640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989881.0, "min": 29952.0, "max": 989881.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989881.0, "min": 29952.0, "max": 989881.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.21934671700000763, "min": -0.107887402176857, "max": 0.24968639016151428, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 55.71406555175781, "min": -25.892976760864258, "max": 64.16940307617188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01428283378481865, "min": -0.0028907437808811665, "max": 0.1138405054807663, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.6278398036956787, "min": -0.6851062774658203, "max": 27.435562133789062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06751152820721644, "min": 0.06435350195145556, "max": 0.07355268837972771, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9451613949010302, "min": 0.48188125453327363, "max": 1.043961114999975, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009542512685497754, "min": 3.149713154853647e-05, "max": 0.013559358486894607, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13359517759696854, "min": 0.0002834741839368282, "max": 0.1898310188165245, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.6244260299857105e-06, "min": 7.6244260299857105e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010674196441979995, "min": 0.00010674196441979995, "max": 0.0025974253341915997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254144285714285, "min": 0.10254144285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355802, "min": 1.3886848, "max": 2.1913343, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026389014142857135, "min": 0.00026389014142857135, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003694461979999999, "min": 0.003694461979999999, "max": 0.08659425915999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007800370920449495, "min": 0.007800370920449495, "max": 0.26026371121406555, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10920519381761551, "min": 0.10816393047571182, "max": 1.8218460083007812, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 635.8085106382979, "min": 585.9444444444445, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29883.0, "min": 15984.0, "max": 32961.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8959574114452017, "min": -1.0000000521540642, "max": 1.1917481272032968, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 42.10999833792448, "min": -31.99920167028904, "max": 64.35439886897802, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8959574114452017, "min": -1.0000000521540642, "max": 1.1917481272032968, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 42.10999833792448, "min": -31.99920167028904, "max": 64.35439886897802, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.052254310346820314, "min": 0.05041510572751846, "max": 6.400271826423705, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4559525863005547, "min": 1.7988217025995255, "max": 102.40434922277927, "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": "1717144661", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717146603" }, "total": 1942.1668145609997, "count": 1, "self": 0.6300001509998765, "children": { "run_training.setup": { "total": 0.08387950099995578, "count": 1, "self": 0.08387950099995578 }, "TrainerController.start_learning": { "total": 1941.4529349089999, "count": 1, "self": 1.2427246619113248, "children": { "TrainerController._reset_env": { "total": 2.66682578200016, "count": 1, "self": 2.66682578200016 }, "TrainerController.advance": { "total": 1937.4197996340886, "count": 63175, "self": 1.2777192430612558, "children": { "env_step": { "total": 1320.3516024949963, "count": 63175, "self": 1194.2856554618702, "children": { "SubprocessEnvManager._take_step": { "total": 125.32499061105, "count": 63175, "self": 4.375731789038127, "children": { "TorchPolicy.evaluate": { "total": 120.94925882201187, "count": 62553, "self": 120.94925882201187 } } }, "workers": { "total": 0.740956422076124, "count": 63175, "self": 0.0, "children": { "worker_root": { "total": 1937.1857722879927, "count": 63175, "is_parallel": true, "self": 853.6947031099367, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027836150002258364, "count": 1, "is_parallel": true, "self": 0.0007376380003734084, "children": { "_process_rank_one_or_two_observation": { "total": 0.002045976999852428, "count": 8, "is_parallel": true, "self": 0.002045976999852428 } } }, "UnityEnvironment.step": { "total": 0.04955032299994855, "count": 1, "is_parallel": true, "self": 0.0006210080000528251, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005180419998396246, "count": 1, "is_parallel": true, "self": 0.0005180419998396246 }, "communicator.exchange": { "total": 0.04678118599986192, "count": 1, "is_parallel": true, "self": 0.04678118599986192 }, "steps_from_proto": { "total": 0.0016300870001941803, "count": 1, "is_parallel": true, "self": 0.0003778209998017701, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012522660003924102, "count": 8, "is_parallel": true, "self": 0.0012522660003924102 } } } } } } }, "UnityEnvironment.step": { "total": 1083.491069178056, "count": 63174, "is_parallel": true, "self": 32.33792323498119, "children": { "UnityEnvironment._generate_step_input": { "total": 22.71441549209203, "count": 63174, "is_parallel": true, "self": 22.71441549209203 }, "communicator.exchange": { "total": 933.5516532139027, "count": 63174, "is_parallel": true, "self": 933.5516532139027 }, "steps_from_proto": { "total": 94.88707723708012, "count": 63174, "is_parallel": true, "self": 18.63369781083111, "children": { "_process_rank_one_or_two_observation": { "total": 76.25337942624901, "count": 505392, "is_parallel": true, "self": 76.25337942624901 } } } } } } } } } } }, "trainer_advance": { "total": 615.790477896031, "count": 63175, "self": 2.0201169819956704, "children": { "process_trajectory": { "total": 119.81405286104246, "count": 63175, "self": 119.57973079304247, "children": { "RLTrainer._checkpoint": { "total": 0.23432206799998312, "count": 2, "self": 0.23432206799998312 } } }, "_update_policy": { "total": 493.9563080529929, "count": 414, "self": 291.5795498030616, "children": { "TorchPPOOptimizer.update": { "total": 202.3767582499313, "count": 22965, "self": 202.3767582499313 } } } } } } }, "trainer_threads": { "total": 1.4090001059230417e-06, "count": 1, "self": 1.4090001059230417e-06 }, "TrainerController._save_models": { "total": 0.1235834219996832, "count": 1, "self": 0.0019075529999099672, "children": { "RLTrainer._checkpoint": { "total": 0.12167586899977323, "count": 1, "self": 0.12167586899977323 } } } } } } }