{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8218531012535095, "min": 0.8218531012535095, "max": 1.4017139673233032, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 24787.08984375, "min": 22427.423828125, "max": 38343.68359375, "count": 16 }, "Pyramids.Step.mean": { "value": 479892.0, "min": 29983.0, "max": 479892.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479892.0, "min": 29983.0, "max": 479892.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.16719870269298553, "min": -0.09453507512807846, "max": 0.18006311357021332, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 41.79967498779297, "min": -22.499347686767578, "max": 45.19584274291992, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04031394422054291, "min": 0.008605342358350754, "max": 0.4116668403148651, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.078486442565918, "min": 2.1169142723083496, "max": 66.13185119628906, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07071494894710777, "min": 0.06409087616463414, "max": 0.07432501029365489, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9900092852595088, "min": 0.22297503088096465, "max": 1.0283716070727107, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01113278306284984, "min": 0.0015895596431628114, "max": 0.01113278306284984, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15585896287989776, "min": 0.008619954277795236, "max": 0.15585896287989776, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.0581250282471426e-05, "min": 2.0581250282471426e-05, "max": 0.0002865078044974, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00028813750395459994, "min": 0.00028813750395459994, "max": 0.0028506831497724003, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10686038571428572, "min": 0.10686038571428572, "max": 0.1955026, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4960454, "min": 0.5865078, "max": 2.3381796, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0006953525328571428, "min": 0.0006953525328571428, "max": 0.009550709740000001, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.00973493546, "min": 0.00973493546, "max": 0.09505773724000002, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016086162999272346, "min": 0.015609530732035637, "max": 0.23164601624011993, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22520627081394196, "min": 0.21853342652320862, "max": 1.1311066150665283, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 658.0909090909091, "min": 656.1777777777778, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28956.0, "min": 15984.0, "max": 32536.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7508090504191138, "min": -1.0000000521540642, "max": 0.7508090504191138, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 33.03559821844101, "min": -26.086401507258415, "max": 33.03559821844101, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7508090504191138, "min": -1.0000000521540642, "max": 0.7508090504191138, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 33.03559821844101, "min": -26.086401507258415, "max": 33.03559821844101, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1074948328314349, "min": 0.10620525570638063, "max": 2.8118732445515118, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 4.729772644583136, "min": 4.729772644583136, "max": 36.554352179169655, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1736783484", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736784508" }, "total": 1024.626133001, "count": 1, "self": 0.4771244139999453, "children": { "run_training.setup": { "total": 0.05486030099996242, "count": 1, "self": 0.05486030099996242 }, "TrainerController.start_learning": { "total": 1024.094148286, "count": 1, "self": 0.6168152419968465, "children": { "TrainerController._reset_env": { "total": 2.1712185540000064, "count": 1, "self": 2.1712185540000064 }, "TrainerController.advance": { "total": 1021.2239919380033, "count": 30786, "self": 0.6336862899715925, "children": { "env_step": { "total": 695.8379171090241, "count": 30786, "self": 625.2730052410059, "children": { "SubprocessEnvManager._take_step": { "total": 70.18478575300469, "count": 30786, "self": 2.1632423169855883, "children": { "TorchPolicy.evaluate": { "total": 68.0215434360191, "count": 30436, "self": 68.0215434360191 } } }, "workers": { "total": 0.3801261150135815, "count": 30786, "self": 0.0, "children": { "worker_root": { "total": 1021.860913875991, "count": 30786, "is_parallel": true, "self": 451.09090727198486, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00209486099993228, "count": 1, "is_parallel": true, "self": 0.0006973370000196155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013975239999126643, "count": 8, "is_parallel": true, "self": 0.0013975239999126643 } } }, "UnityEnvironment.step": { "total": 0.0452558769998177, "count": 1, "is_parallel": true, "self": 0.0005682189998879039, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004359550000572199, "count": 1, "is_parallel": true, "self": 0.0004359550000572199 }, "communicator.exchange": { "total": 0.04256188099998326, "count": 1, "is_parallel": true, "self": 0.04256188099998326 }, "steps_from_proto": { "total": 0.0016898219998893182, "count": 1, "is_parallel": true, "self": 0.0003678539997054031, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013219680001839151, "count": 8, "is_parallel": true, "self": 0.0013219680001839151 } } } } } } }, "UnityEnvironment.step": { "total": 570.7700066040061, "count": 30785, "is_parallel": true, "self": 15.56219973903876, "children": { "UnityEnvironment._generate_step_input": { "total": 11.16187519201435, "count": 30785, "is_parallel": true, "self": 11.16187519201435 }, "communicator.exchange": { "total": 497.36558166495774, "count": 30785, "is_parallel": true, "self": 497.36558166495774 }, "steps_from_proto": { "total": 46.68035000799523, "count": 30785, "is_parallel": true, "self": 9.347248153031842, "children": { "_process_rank_one_or_two_observation": { "total": 37.33310185496339, "count": 246280, "is_parallel": true, "self": 37.33310185496339 } } } } } } } } } } }, "trainer_advance": { "total": 324.7523885390076, "count": 30786, "self": 1.1181802269559284, "children": { "process_trajectory": { "total": 62.56286166304949, "count": 30786, "self": 62.44559191104986, "children": { "RLTrainer._checkpoint": { "total": 0.11726975199962908, "count": 1, "self": 0.11726975199962908 } } }, "_update_policy": { "total": 261.0713466490022, "count": 210, "self": 147.64122675499607, "children": { "TorchPPOOptimizer.update": { "total": 113.43011989400611, "count": 11070, "self": 113.43011989400611 } } } } } } }, "trainer_threads": { "total": 9.169998520519584e-07, "count": 1, "self": 9.169998520519584e-07 }, "TrainerController._save_models": { "total": 0.08212163500002134, "count": 1, "self": 0.0020013969997307868, "children": { "RLTrainer._checkpoint": { "total": 0.08012023800029056, "count": 1, "self": 0.08012023800029056 } } } } } } }