{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5313839316368103, "min": 0.5184337496757507, "max": 1.59465754032135, "count": 30 }, "Pyramids.Policy.Entropy.sum": { "value": 5126.7919921875, "min": 5093.09326171875, "max": 16329.29296875, "count": 30 }, "Pyramids.Step.mean": { "value": 299885.0, "min": 9984.0, "max": 299885.0, "count": 30 }, "Pyramids.Step.sum": { "value": 299885.0, "min": 9984.0, "max": 299885.0, "count": 30 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.039451178163290024, "min": -0.09713312983512878, "max": 0.005632735323160887, "count": 30 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -3.2349965572357178, "min": -7.867783546447754, "max": 0.46751704812049866, "count": 30 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.28675106167793274, "min": 0.28675106167793274, "max": 4.758534908294678, "count": 30 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 23.513587951660156, "min": 23.513587951660156, "max": 385.44134521484375, "count": 30 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06659919462981634, "min": 0.06458665847948378, "max": 0.07921396348625422, "count": 30 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.3329959731490817, "min": 0.14816739533067114, "max": 0.39606981743127107, "count": 30 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.005549917463455738, "min": 0.0007214731828929779, "max": 2.6744915254724524, "count": 30 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.02774958731727869, "min": 0.0036073659144648896, "max": 5.348983050944905, "count": 30 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.829431767466678e-06, "min": 7.829431767466678e-06, "max": 0.0004897600020479999, "count": 30 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.914715883733339e-05, "min": 3.914715883733339e-05, "max": 0.001877886791089333, "count": 30 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10156586666666667, "min": 0.10156586666666667, "max": 0.19795200000000002, "count": 30 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.5078293333333334, "min": 0.39057066666666673, "max": 0.8755773333333334, "count": 30 }, "Pyramids.Policy.Beta.mean": { "value": 0.0001664300800000002, "min": 0.0001664300800000002, "max": 0.009795404800000001, "count": 30 }, "Pyramids.Policy.Beta.sum": { "value": 0.000832150400000001, "min": 0.000832150400000001, "max": 0.037570175600000005, "count": 30 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.04801112040877342, "min": 0.04801112040877342, "max": 1.7646175622940063, "count": 30 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2400556057691574, "min": 0.2138153612613678, "max": 3.5292351245880127, "count": 30 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 902.6923076923077, "min": 789.0, "max": 999.0, "count": 29 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 11735.0, "min": 789.0, "max": 15984.0, "count": 29 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.2877538834626858, "min": -1.0000000521540642, "max": 1.2109999358654022, "count": 29 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -3.7408004850149155, "min": -16.000000834465027, "max": 1.2109999358654022, "count": 29 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.2877538834626858, "min": -1.0000000521540642, "max": 1.2109999358654022, "count": 29 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -3.7408004850149155, "min": -16.000000834465027, "max": 1.2109999358654022, "count": 29 }, "Pyramids.Policy.RndReward.mean": { "value": 2.248917204829363, "min": 2.248917204829363, "max": 113.37435679137707, "count": 29 }, "Pyramids.Policy.RndReward.sum": { "value": 29.235923662781715, "min": 17.16025671362877, "max": 1813.989708662033, "count": 29 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1728313768", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728314610" }, "total": 841.6716424780002, "count": 1, "self": 1.2226194330000908, "children": { "run_training.setup": { "total": 0.07048000999975557, "count": 1, "self": 0.07048000999975557 }, "TrainerController.start_learning": { "total": 840.3785430350003, "count": 1, "self": 0.7278264639689951, "children": { "TrainerController._reset_env": { "total": 2.1418418749999546, "count": 1, "self": 2.1418418749999546 }, "TrainerController.advance": { "total": 837.4002390130313, "count": 18960, "self": 0.8135929070281236, "children": { "env_step": { "total": 614.3581447360061, "count": 18960, "self": 571.7373430280154, "children": { "SubprocessEnvManager._take_step": { "total": 42.185202114984804, "count": 18960, "self": 2.2292223449462654, "children": { "TorchPolicy.evaluate": { "total": 39.95597977003854, "count": 18803, "self": 39.95597977003854 } } }, "workers": { "total": 0.435599593005918, "count": 18960, "self": 0.0, "children": { "worker_root": { "total": 838.1444552279972, "count": 18960, "is_parallel": true, "self": 324.62054183996815, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029286159997354844, "count": 1, "is_parallel": true, "self": 0.000948376999986067, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019802389997494174, "count": 8, "is_parallel": true, "self": 0.0019802389997494174 } } }, "UnityEnvironment.step": { "total": 0.06471674900012658, "count": 1, "is_parallel": true, "self": 0.0008223410000027798, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005496369999491435, "count": 1, "is_parallel": true, "self": 0.0005496369999491435 }, "communicator.exchange": { "total": 0.0597803919999933, "count": 1, "is_parallel": true, "self": 0.0597803919999933 }, "steps_from_proto": { "total": 0.0035643790001813613, "count": 1, "is_parallel": true, "self": 0.0004760600008921756, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030883189992891857, "count": 8, "is_parallel": true, "self": 0.0030883189992891857 } } } } } } }, "UnityEnvironment.step": { "total": 513.5239133880291, "count": 18959, "is_parallel": true, "self": 15.362981307011978, "children": { "UnityEnvironment._generate_step_input": { "total": 9.676796632009882, "count": 18959, "is_parallel": true, "self": 9.676796632009882 }, "communicator.exchange": { "total": 449.0799627340075, "count": 18959, "is_parallel": true, "self": 449.0799627340075 }, "steps_from_proto": { "total": 39.40417271499973, "count": 18959, "is_parallel": true, "self": 8.550509574921307, "children": { "_process_rank_one_or_two_observation": { "total": 30.853663140078424, "count": 151672, "is_parallel": true, "self": 30.853663140078424 } } } } } } } } } } }, "trainer_advance": { "total": 222.22850136999705, "count": 18960, "self": 1.2491594040452583, "children": { "process_trajectory": { "total": 45.57653859195307, "count": 18960, "self": 45.57653859195307 }, "_update_policy": { "total": 175.40280337399872, "count": 127, "self": 108.74284132002003, "children": { "TorchPPOOptimizer.update": { "total": 66.65996205397869, "count": 6864, "self": 66.65996205397869 } } } } } } }, "trainer_threads": { "total": 1.5430000530614052e-06, "count": 1, "self": 1.5430000530614052e-06 }, "TrainerController._save_models": { "total": 0.10863414000004923, "count": 1, "self": 0.0009575519998179516, "children": { "RLTrainer._checkpoint": { "total": 0.10767658800023128, "count": 1, "self": 0.10767658800023128 } } } } } } }