{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.434438556432724, "min": 0.434438556432724, "max": 1.4825477600097656, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13040.107421875, "min": 13040.107421875, "max": 44974.5703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989944.0, "min": 29952.0, "max": 989944.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989944.0, "min": 29952.0, "max": 989944.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5481445789337158, "min": -0.11050743609666824, "max": 0.5541549921035767, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.48048400878906, "min": -26.52178382873535, "max": 153.48048400878906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03418660908937454, "min": 0.00025613995967432857, "max": 0.2820543348789215, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.572250366210938, "min": 0.06505955010652542, "max": 66.84687805175781, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07174982456213218, "min": 0.06467532314790732, "max": 0.07364948674512561, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0044975438698505, "min": 0.5095350571189493, "max": 1.07207304124798, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015388577774934848, "min": 0.0006989499164246515, "max": 0.01629652920291082, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21544008884908786, "min": 0.009086348913520469, "max": 0.2281514088407515, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.515097495000001e-06, "min": 7.515097495000001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010521136493000002, "min": 0.00010521136493000002, "max": 0.003507825830724799, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.102505, "min": 0.102505, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.43507, "min": 1.3886848, "max": 2.5722929, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026024950000000006, "min": 0.00026024950000000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036434930000000007, "min": 0.0036434930000000007, "max": 0.11695059247999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010728736408054829, "min": 0.010573171079158783, "max": 0.27186617255210876, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15020230412483215, "min": 0.14802439510822296, "max": 1.903063178062439, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 340.71590909090907, "min": 340.71590909090907, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29983.0, "min": 15984.0, "max": 33563.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5683477040888234, "min": -1.0000000521540642, "max": 1.5831048564939965, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 138.01459795981646, "min": -30.371001690626144, "max": 138.01459795981646, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5683477040888234, "min": -1.0000000521540642, "max": 1.5831048564939965, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 138.01459795981646, "min": -30.371001690626144, "max": 138.01459795981646, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0382815630883587, "min": 0.0382815630883587, "max": 5.356797653250396, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3687775517755654, "min": 3.1710653340778663, "max": 85.70876245200634, "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": "1766039416", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/miniconda/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsRND1 --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": "1766041134" }, "total": 1718.5871716379997, "count": 1, "self": 0.3223657599994567, "children": { "run_training.setup": { "total": 0.024433458999965296, "count": 1, "self": 0.024433458999965296 }, "TrainerController.start_learning": { "total": 1718.2403724190003, "count": 1, "self": 1.443068880032115, "children": { "TrainerController._reset_env": { "total": 2.2331358019999925, "count": 1, "self": 2.2331358019999925 }, "TrainerController.advance": { "total": 1714.4844808529679, "count": 63875, "self": 1.3658755749984266, "children": { "env_step": { "total": 1078.2446347359808, "count": 63875, "self": 928.3280833140449, "children": { "SubprocessEnvManager._take_step": { "total": 149.08115796797995, "count": 63875, "self": 4.463717564960689, "children": { "TorchPolicy.evaluate": { "total": 144.61744040301926, "count": 62580, "self": 144.61744040301926 } } }, "workers": { "total": 0.8353934539559305, "count": 63875, "self": 0.0, "children": { "worker_root": { "total": 1715.9177715950136, "count": 63875, "is_parallel": true, "self": 879.7594169019849, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018511370000169336, "count": 1, "is_parallel": true, "self": 0.0006115879999697427, "children": { "_process_rank_one_or_two_observation": { "total": 0.001239549000047191, "count": 8, "is_parallel": true, "self": 0.001239549000047191 } } }, "UnityEnvironment.step": { "total": 0.03572563599993828, "count": 1, "is_parallel": true, "self": 0.00034188799997991737, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029936199996427604, "count": 1, "is_parallel": true, "self": 0.00029936199996427604 }, "communicator.exchange": { "total": 0.034006331999989925, "count": 1, "is_parallel": true, "self": 0.034006331999989925 }, "steps_from_proto": { "total": 0.0010780540000041583, "count": 1, "is_parallel": true, "self": 0.00028356799998618953, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007944860000179688, "count": 8, "is_parallel": true, "self": 0.0007944860000179688 } } } } } } }, "UnityEnvironment.step": { "total": 836.1583546930287, "count": 63874, "is_parallel": true, "self": 20.568678346981073, "children": { "UnityEnvironment._generate_step_input": { "total": 13.922366450012191, "count": 63874, "is_parallel": true, "self": 13.922366450012191 }, "communicator.exchange": { "total": 741.5726848570196, "count": 63874, "is_parallel": true, "self": 741.5726848570196 }, "steps_from_proto": { "total": 60.09462503901591, "count": 63874, "is_parallel": true, "self": 12.836633554082482, "children": { "_process_rank_one_or_two_observation": { "total": 47.25799148493343, "count": 510992, "is_parallel": true, "self": 47.25799148493343 } } } } } } } } } } }, "trainer_advance": { "total": 634.8739705419886, "count": 63875, "self": 2.7314036340095527, "children": { "process_trajectory": { "total": 117.74216701998216, "count": 63875, "self": 117.55867295698226, "children": { "RLTrainer._checkpoint": { "total": 0.18349406299989823, "count": 2, "self": 0.18349406299989823 } } }, "_update_policy": { "total": 514.4003998879969, "count": 452, "self": 282.3409292730224, "children": { "TorchPPOOptimizer.update": { "total": 232.05947061497443, "count": 22803, "self": 232.05947061497443 } } } } } } }, "trainer_threads": { "total": 9.959999260900076e-07, "count": 1, "self": 9.959999260900076e-07 }, "TrainerController._save_models": { "total": 0.07968588800031284, "count": 1, "self": 0.001187908000247262, "children": { "RLTrainer._checkpoint": { "total": 0.07849798000006558, "count": 1, "self": 0.07849798000006558 } } } } } } }