{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43061599135398865, "min": 0.41969695687294006, "max": 1.5029531717300415, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12939.1494140625, "min": 12543.90234375, "max": 45593.5859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5647550225257874, "min": -0.295282244682312, "max": 0.5647550225257874, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 158.6961669921875, "min": -69.98189544677734, "max": 158.6961669921875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026229623705148697, "min": 0.004407207015901804, "max": 0.27302539348602295, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.3705244064331055, "min": 1.1194305419921875, "max": 64.70701599121094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06930100012536218, "min": 0.06527865503379698, "max": 0.07298839547396344, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9702140017550704, "min": 0.4854842502335769, "max": 1.0599958506622809, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015003745682248637, "min": 0.0002668970858902249, "max": 0.01546745826552996, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21005243955148092, "min": 0.0032027650306826988, "max": 0.23201187398294942, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.403368960814286e-06, "min": 7.403368960814286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010364716545140001, "min": 0.00010364716545140001, "max": 0.003493071735642799, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246775714285716, "min": 0.10246775714285716, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345486000000003, "min": 1.3886848, "max": 2.5277195, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025652893857142865, "min": 0.00025652893857142865, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003591405140000001, "min": 0.003591405140000001, "max": 0.11644928428000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0094130989164114, "min": 0.0094130989164114, "max": 0.37298470735549927, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1317833811044693, "min": 0.1317833811044693, "max": 2.6108930110931396, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 339.9555555555556, "min": 339.9555555555556, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30596.0, "min": 15984.0, "max": 32931.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5892763867806852, "min": -1.0000000521540642, "max": 1.5892763867806852, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 141.445598423481, "min": -30.99680159986019, "max": 141.445598423481, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5892763867806852, "min": -1.0000000521540642, "max": 1.5892763867806852, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 141.445598423481, "min": -30.99680159986019, "max": 141.445598423481, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.033504560196725125, "min": 0.033504560196725125, "max": 7.782965171150863, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9819058575085364, "min": 2.7984274235204794, "max": 124.52744273841381, "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": "1754160802", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1754163001" }, "total": 2198.7186733400004, "count": 1, "self": 0.5035922120005125, "children": { "run_training.setup": { "total": 0.0302994819999185, "count": 1, "self": 0.0302994819999185 }, "TrainerController.start_learning": { "total": 2198.184781646, "count": 1, "self": 1.4420345789912972, "children": { "TrainerController._reset_env": { "total": 3.8243558159999793, "count": 1, "self": 3.8243558159999793 }, "TrainerController.advance": { "total": 2192.8370419900084, "count": 63812, "self": 1.4567778070754684, "children": { "env_step": { "total": 1529.7202656089219, "count": 63812, "self": 1374.3730888040388, "children": { "SubprocessEnvManager._take_step": { "total": 154.48543872189202, "count": 63812, "self": 4.680523751836063, "children": { "TorchPolicy.evaluate": { "total": 149.80491497005596, "count": 62565, "self": 149.80491497005596 } } }, "workers": { "total": 0.8617380829909962, "count": 63812, "self": 0.0, "children": { "worker_root": { "total": 2192.6141194170063, "count": 63812, "is_parallel": true, "self": 934.7750163129747, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0061965869999767165, "count": 1, "is_parallel": true, "self": 0.004286679000188087, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019099079997886292, "count": 8, "is_parallel": true, "self": 0.0019099079997886292 } } }, "UnityEnvironment.step": { "total": 0.045272622999846135, "count": 1, "is_parallel": true, "self": 0.0005224669998824538, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004478379999000026, "count": 1, "is_parallel": true, "self": 0.0004478379999000026 }, "communicator.exchange": { "total": 0.04273516600005678, "count": 1, "is_parallel": true, "self": 0.04273516600005678 }, "steps_from_proto": { "total": 0.0015671520000068995, "count": 1, "is_parallel": true, "self": 0.0003405740001198865, "children": { "_process_rank_one_or_two_observation": { "total": 0.001226577999887013, "count": 8, "is_parallel": true, "self": 0.001226577999887013 } } } } } } }, "UnityEnvironment.step": { "total": 1257.8391031040317, "count": 63811, "is_parallel": true, "self": 32.467421718918104, "children": { "UnityEnvironment._generate_step_input": { "total": 23.525194450016443, "count": 63811, "is_parallel": true, "self": 23.525194450016443 }, "communicator.exchange": { "total": 1103.3724404750478, "count": 63811, "is_parallel": true, "self": 1103.3724404750478 }, "steps_from_proto": { "total": 98.4740464600493, "count": 63811, "is_parallel": true, "self": 20.11190492012588, "children": { "_process_rank_one_or_two_observation": { "total": 78.36214153992341, "count": 510488, "is_parallel": true, "self": 78.36214153992341 } } } } } } } } } } }, "trainer_advance": { "total": 661.6599985740111, "count": 63812, "self": 2.7658128809737264, "children": { "process_trajectory": { "total": 129.72595446103742, "count": 63812, "self": 129.50190017703744, "children": { "RLTrainer._checkpoint": { "total": 0.22405428399997618, "count": 2, "self": 0.22405428399997618 } } }, "_update_policy": { "total": 529.1682312319999, "count": 447, "self": 294.97655216398516, "children": { "TorchPPOOptimizer.update": { "total": 234.19167906801476, "count": 22842, "self": 234.19167906801476 } } } } } } }, "trainer_threads": { "total": 8.580000212532468e-07, "count": 1, "self": 8.580000212532468e-07 }, "TrainerController._save_models": { "total": 0.08134840299999269, "count": 1, "self": 0.0013538579996748012, "children": { "RLTrainer._checkpoint": { "total": 0.07999454500031788, "count": 1, "self": 0.07999454500031788 } } } } } } }