{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.32650652527809143, "min": 0.32650652527809143, "max": 1.4369393587112427, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9758.626953125, "min": 9758.626953125, "max": 43590.9921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5574238300323486, "min": -0.10312509536743164, "max": 0.5867995619773865, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.2915496826172, "min": -24.853147506713867, "max": 161.369873046875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0083937281742692, "min": -0.006542567163705826, "max": 0.4972696304321289, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.3082752227783203, "min": -1.7403228282928467, "max": 117.8529052734375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06395071418955921, "min": 0.06395071418955921, "max": 0.07490960157078566, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.895309998653829, "min": 0.47911628671746503, "max": 1.0822750393805716, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016422373473428054, "min": 0.0005674821517405133, "max": 0.01750672020643222, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22991322862799277, "min": 0.007377267972626673, "max": 0.24509408289005105, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.469433224507145e-06, "min": 7.469433224507145e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010457206514310004, "min": 0.00010457206514310004, "max": 0.0033774859741713993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248977857142857, "min": 0.10248977857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348569, "min": 1.3691136000000002, "max": 2.4426284, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002587288792857144, "min": 0.0002587288792857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036222043100000018, "min": 0.0036222043100000018, "max": 0.11260027714, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010120958089828491, "min": 0.010120958089828491, "max": 0.47570323944091797, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14169341325759888, "min": 0.14169341325759888, "max": 3.329922676086426, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 301.5833333333333, "min": 301.5833333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 25333.0, "min": 15984.0, "max": 33053.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6745999845720472, "min": -1.0000000521540642, "max": 1.6770666498276923, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 140.66639870405197, "min": -32.000001668930054, "max": 150.9359984844923, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6745999845720472, "min": -1.0000000521540642, "max": 1.6770666498276923, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 140.66639870405197, "min": -32.000001668930054, "max": 150.9359984844923, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03223150846315548, "min": 0.03223150846315548, "max": 9.903113841079175, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.70744671090506, "min": 2.70744671090506, "max": 158.4498214572668, "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": "1739346974", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739349217" }, "total": 2242.539722183, "count": 1, "self": 1.0060391319998416, "children": { "run_training.setup": { "total": 0.023453064000023005, "count": 1, "self": 0.023453064000023005 }, "TrainerController.start_learning": { "total": 2241.510229987, "count": 1, "self": 1.343092004005939, "children": { "TrainerController._reset_env": { "total": 3.0127092909999647, "count": 1, "self": 3.0127092909999647 }, "TrainerController.advance": { "total": 2237.0153538289937, "count": 63817, "self": 1.3625168340331584, "children": { "env_step": { "total": 1558.8470184549797, "count": 63817, "self": 1404.0170486679585, "children": { "SubprocessEnvManager._take_step": { "total": 154.04180591902434, "count": 63817, "self": 4.624732182061734, "children": { "TorchPolicy.evaluate": { "total": 149.4170737369626, "count": 62579, "self": 149.4170737369626 } } }, "workers": { "total": 0.7881638679969001, "count": 63817, "self": 0.0, "children": { "worker_root": { "total": 2236.5790920240274, "count": 63817, "is_parallel": true, "self": 943.6132619479574, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004993763000015861, "count": 1, "is_parallel": true, "self": 0.0035939199999575067, "children": { "_process_rank_one_or_two_observation": { "total": 0.001399843000058354, "count": 8, "is_parallel": true, "self": 0.001399843000058354 } } }, "UnityEnvironment.step": { "total": 0.04909913099993446, "count": 1, "is_parallel": true, "self": 0.000532895999754146, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004993040000726978, "count": 1, "is_parallel": true, "self": 0.0004993040000726978 }, "communicator.exchange": { "total": 0.04613801200002854, "count": 1, "is_parallel": true, "self": 0.04613801200002854 }, "steps_from_proto": { "total": 0.0019289190000790768, "count": 1, "is_parallel": true, "self": 0.0004981849999694532, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014307340001096236, "count": 8, "is_parallel": true, "self": 0.0014307340001096236 } } } } } } }, "UnityEnvironment.step": { "total": 1292.96583007607, "count": 63816, "is_parallel": true, "self": 32.03054396507969, "children": { "UnityEnvironment._generate_step_input": { "total": 22.802995531992906, "count": 63816, "is_parallel": true, "self": 22.802995531992906 }, "communicator.exchange": { "total": 1142.766620478022, "count": 63816, "is_parallel": true, "self": 1142.766620478022 }, "steps_from_proto": { "total": 95.3656701009752, "count": 63816, "is_parallel": true, "self": 19.207014058077107, "children": { "_process_rank_one_or_two_observation": { "total": 76.15865604289809, "count": 510528, "is_parallel": true, "self": 76.15865604289809 } } } } } } } } } } }, "trainer_advance": { "total": 676.8058185399809, "count": 63817, "self": 2.7134836570141943, "children": { "process_trajectory": { "total": 128.26368387696186, "count": 63817, "self": 127.93805140696202, "children": { "RLTrainer._checkpoint": { "total": 0.32563246999984585, "count": 2, "self": 0.32563246999984585 } } }, "_update_policy": { "total": 545.8286510060049, "count": 446, "self": 298.8231056210267, "children": { "TorchPPOOptimizer.update": { "total": 247.00554538497818, "count": 22809, "self": 247.00554538497818 } } } } } } }, "trainer_threads": { "total": 1.4120000741968397e-06, "count": 1, "self": 1.4120000741968397e-06 }, "TrainerController._save_models": { "total": 0.1390734510000584, "count": 1, "self": 0.0020448070004022156, "children": { "RLTrainer._checkpoint": { "total": 0.1370286439996562, "count": 1, "self": 0.1370286439996562 } } } } } } }