{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3337717652320862, "min": 0.3337717652320862, "max": 1.5191583633422852, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10029.173828125, "min": 10029.173828125, "max": 46085.1875, "count": 33 }, "Pyramids.Step.mean": { "value": 989953.0, "min": 29952.0, "max": 989953.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989953.0, "min": 29952.0, "max": 989953.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6208828687667847, "min": -0.11849431693553925, "max": 0.6698364615440369, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 174.46807861328125, "min": -28.557130813598633, "max": 187.55421447753906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0009937218856066465, "min": -0.019251415506005287, "max": 0.34368908405303955, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.27923583984375, "min": -5.313390731811523, "max": 81.45431518554688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06637975936029164, "min": 0.06516393746382423, "max": 0.07374133162721548, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.929316631044083, "min": 0.4989270236180565, "max": 1.0572909826199368, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015151303585899823, "min": 0.0010113535707143462, "max": 0.015542685259355319, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21211825020259753, "min": 0.010113535707143462, "max": 0.21759759363097447, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.335868983314283e-06, "min": 7.335868983314283e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010270216576639996, "min": 0.00010270216576639996, "max": 0.0036319081893640007, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244525714285715, "min": 0.10244525714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342336000000002, "min": 1.3886848, "max": 2.6106360000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002542811885714285, "min": 0.0002542811885714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035599366399999993, "min": 0.0035599366399999993, "max": 0.1210825364, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008479451760649681, "min": 0.008479451760649681, "max": 0.29954075813293457, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11871232092380524, "min": 0.11871232092380524, "max": 2.096785306930542, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 302.71875, "min": 302.35, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29061.0, "min": 15984.0, "max": 32641.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6554399833867424, "min": -1.0000000521540642, "max": 1.6976499779522418, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 157.26679842174053, "min": -30.673001691699028, "max": 169.7649977952242, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6554399833867424, "min": -1.0000000521540642, "max": 1.6976499779522418, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 157.26679842174053, "min": -30.673001691699028, "max": 169.7649977952242, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.026382080173291463, "min": 0.026382080173291463, "max": 5.897820483893156, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.506297616462689, "min": 2.506297616462689, "max": 94.3651277422905, "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": "1738686258", "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": "1738688452" }, "total": 2194.305023733, "count": 1, "self": 1.046406025000124, "children": { "run_training.setup": { "total": 0.019117225000172766, "count": 1, "self": 0.019117225000172766 }, "TrainerController.start_learning": { "total": 2193.2395004829996, "count": 1, "self": 1.4057130960700306, "children": { "TrainerController._reset_env": { "total": 2.147486917000151, "count": 1, "self": 2.147486917000151 }, "TrainerController.advance": { "total": 2189.5626948579297, "count": 64026, "self": 1.4098507568364766, "children": { "env_step": { "total": 1511.201577152018, "count": 64026, "self": 1359.1689895409907, "children": { "SubprocessEnvManager._take_step": { "total": 151.2471676330449, "count": 64026, "self": 4.630914103966688, "children": { "TorchPolicy.evaluate": { "total": 146.61625352907822, "count": 62542, "self": 146.61625352907822 } } }, "workers": { "total": 0.7854199779824285, "count": 64026, "self": 0.0, "children": { "worker_root": { "total": 2188.0335371170563, "count": 64026, "is_parallel": true, "self": 940.2210750621318, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019958039999892208, "count": 1, "is_parallel": true, "self": 0.0006930829997600085, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013027210002292122, "count": 8, "is_parallel": true, "self": 0.0013027210002292122 } } }, "UnityEnvironment.step": { "total": 0.054009006999876874, "count": 1, "is_parallel": true, "self": 0.000681002999726843, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005722089999835589, "count": 1, "is_parallel": true, "self": 0.0005722089999835589 }, "communicator.exchange": { "total": 0.0507717320001575, "count": 1, "is_parallel": true, "self": 0.0507717320001575 }, "steps_from_proto": { "total": 0.001984063000008973, "count": 1, "is_parallel": true, "self": 0.0004885350006134104, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014955279993955628, "count": 8, "is_parallel": true, "self": 0.0014955279993955628 } } } } } } }, "UnityEnvironment.step": { "total": 1247.8124620549245, "count": 64025, "is_parallel": true, "self": 31.011972563876043, "children": { "UnityEnvironment._generate_step_input": { "total": 22.960942003004902, "count": 64025, "is_parallel": true, "self": 22.960942003004902 }, "communicator.exchange": { "total": 1098.8607034740296, "count": 64025, "is_parallel": true, "self": 1098.8607034740296 }, "steps_from_proto": { "total": 94.97884401401393, "count": 64025, "is_parallel": true, "self": 19.133933622868653, "children": { "_process_rank_one_or_two_observation": { "total": 75.84491039114528, "count": 512200, "is_parallel": true, "self": 75.84491039114528 } } } } } } } } } } }, "trainer_advance": { "total": 676.951266949075, "count": 64026, "self": 2.647327563046929, "children": { "process_trajectory": { "total": 128.76076032103379, "count": 64026, "self": 128.49301397903378, "children": { "RLTrainer._checkpoint": { "total": 0.26774634200000946, "count": 2, "self": 0.26774634200000946 } } }, "_update_policy": { "total": 545.5431790649943, "count": 450, "self": 301.0182592379974, "children": { "TorchPPOOptimizer.update": { "total": 244.5249198269969, "count": 22776, "self": 244.5249198269969 } } } } } } }, "trainer_threads": { "total": 1.0589997145871166e-06, "count": 1, "self": 1.0589997145871166e-06 }, "TrainerController._save_models": { "total": 0.1236045529999501, "count": 1, "self": 0.0019112539998786815, "children": { "RLTrainer._checkpoint": { "total": 0.12169329900007142, "count": 1, "self": 0.12169329900007142 } } } } } } }