{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.344311386346817, "min": 0.344311386346817, "max": 1.4628901481628418, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10400.9580078125, "min": 10400.9580078125, "max": 44378.234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5141056776046753, "min": -0.10545001178979874, "max": 0.5141056776046753, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 140.86495971679688, "min": -25.308002471923828, "max": 140.86495971679688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.047437332570552826, "min": -0.04011460766196251, "max": 0.43395787477493286, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.99782943725586, "min": -10.389683723449707, "max": 102.84801483154297, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06991193211611023, "min": 0.06383311819548147, "max": 0.07353577234758192, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9787670496255433, "min": 0.4846380597767259, "max": 1.0295249047048856, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0151693149638057, "min": 0.0007674287948846285, "max": 0.01685575502633583, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2123704094932798, "min": 0.006157973586758236, "max": 0.2528363253950374, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.330318985164286e-06, "min": 7.330318985164286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001026244657923, "min": 0.0001026244657923, "max": 0.0030225965924679, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244340714285714, "min": 0.10244340714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342077, "min": 1.3691136000000002, "max": 2.4006940000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002540963735714286, "min": 0.0002540963735714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035573492300000004, "min": 0.0035573492300000004, "max": 0.10078245678999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0101042864844203, "min": 0.0101042864844203, "max": 0.5560652613639832, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14146001636981964, "min": 0.14146001636981964, "max": 3.8924567699432373, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 371.3544303797468, "min": 364.625, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29337.0, "min": 15984.0, "max": 35090.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5273366859064827, "min": -1.0000000521540642, "max": 1.560359976813197, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 120.65959818661213, "min": -32.000001668930054, "max": 124.82879814505577, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5273366859064827, "min": -1.0000000521540642, "max": 1.560359976813197, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 120.65959818661213, "min": -32.000001668930054, "max": 124.82879814505577, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.038755055155923375, "min": 0.038755055155923375, "max": 11.84042221866548, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.061649357317947, "min": 3.061649357317947, "max": 189.4467554986477, "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": "1783026635", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1783028816" }, "total": 2181.315301639, "count": 1, "self": 0.47730818900072336, "children": { "run_training.setup": { "total": 0.023097411999970063, "count": 1, "self": 0.023097411999970063 }, "TrainerController.start_learning": { "total": 2180.8148960379995, "count": 1, "self": 1.2367860050621857, "children": { "TrainerController._reset_env": { "total": 2.0937128689997735, "count": 1, "self": 2.0937128689997735 }, "TrainerController.advance": { "total": 2177.408450513937, "count": 63602, "self": 1.254918399854887, "children": { "env_step": { "total": 1561.5081976550218, "count": 63602, "self": 1420.4326170380841, "children": { "SubprocessEnvManager._take_step": { "total": 140.34663644995544, "count": 63602, "self": 4.360013851881831, "children": { "TorchPolicy.evaluate": { "total": 135.9866225980736, "count": 62548, "self": 135.9866225980736 } } }, "workers": { "total": 0.7289441669822736, "count": 63602, "self": 0.0, "children": { "worker_root": { "total": 2174.7251825260014, "count": 63602, "is_parallel": true, "self": 864.4544187669735, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017119130002356542, "count": 1, "is_parallel": true, "self": 0.0005394340000748343, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011724790001608199, "count": 8, "is_parallel": true, "self": 0.0011724790001608199 } } }, "UnityEnvironment.step": { "total": 0.04815595399986705, "count": 1, "is_parallel": true, "self": 0.0005156030001671752, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042633900011423975, "count": 1, "is_parallel": true, "self": 0.00042633900011423975 }, "communicator.exchange": { "total": 0.04551495499981684, "count": 1, "is_parallel": true, "self": 0.04551495499981684 }, "steps_from_proto": { "total": 0.0016990569997687999, "count": 1, "is_parallel": true, "self": 0.0003553459991962882, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013437110005725117, "count": 8, "is_parallel": true, "self": 0.0013437110005725117 } } } } } } }, "UnityEnvironment.step": { "total": 1310.270763759028, "count": 63601, "is_parallel": true, "self": 32.758480210103244, "children": { "UnityEnvironment._generate_step_input": { "total": 22.4774664770689, "count": 63601, "is_parallel": true, "self": 22.4774664770689 }, "communicator.exchange": { "total": 1152.1519197048806, "count": 63601, "is_parallel": true, "self": 1152.1519197048806 }, "steps_from_proto": { "total": 102.88289736697516, "count": 63601, "is_parallel": true, "self": 21.06264262888817, "children": { "_process_rank_one_or_two_observation": { "total": 81.82025473808699, "count": 508808, "is_parallel": true, "self": 81.82025473808699 } } } } } } } } } } }, "trainer_advance": { "total": 614.6453344590605, "count": 63602, "self": 2.2813545480685207, "children": { "process_trajectory": { "total": 105.46226016599621, "count": 63602, "self": 105.28006091199586, "children": { "RLTrainer._checkpoint": { "total": 0.18219925400035208, "count": 2, "self": 0.18219925400035208 } } }, "_update_policy": { "total": 506.9017197449957, "count": 436, "self": 273.20783899196704, "children": { "TorchPPOOptimizer.update": { "total": 233.69388075302868, "count": 22812, "self": 233.69388075302868 } } } } } } }, "trainer_threads": { "total": 9.55000359681435e-07, "count": 1, "self": 9.55000359681435e-07 }, "TrainerController._save_models": { "total": 0.07594569499997306, "count": 1, "self": 0.000874651000231097, "children": { "RLTrainer._checkpoint": { "total": 0.07507104399974196, "count": 1, "self": 0.07507104399974196 } } } } } } }