{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6879401803016663, "min": 0.654887855052948, "max": 1.4360133409500122, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20792.3046875, "min": 19531.375, "max": 43562.90234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989925.0, "min": 29952.0, "max": 989925.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989925.0, "min": 29952.0, "max": 989925.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2505187690258026, "min": -0.22013568878173828, "max": 0.2505187690258026, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 63.381248474121094, "min": -52.172157287597656, "max": 63.381248474121094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.013546476140618324, "min": -0.013546476140618324, "max": 0.31149423122406006, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.4272584915161133, "min": -3.4272584915161133, "max": 75.07010650634766, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.061661323940543473, "min": 0.061661323940543473, "max": 0.07331444574391412, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9249198591081521, "min": 0.47261095472096987, "max": 1.0590531569317794, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009954051265873098, "min": 0.00019516668503997064, "max": 0.010586337453114996, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14931076898809648, "min": 0.0025371669055196185, "max": 0.14931076898809648, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.514397495233332e-06, "min": 7.514397495233332e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011271596242849998, "min": 0.00011271596242849998, "max": 0.0036332182889272993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250476666666669, "min": 0.10250476666666669, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375715000000003, "min": 1.3886848, "max": 2.6110727, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026022618999999996, "min": 0.00026022618999999996, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039033928499999995, "min": 0.0039033928499999995, "max": 0.12112616273000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014551150612533092, "min": 0.014551150612533092, "max": 0.3621668219566345, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2182672619819641, "min": 0.2143244445323944, "max": 2.535167694091797, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 632.8, "min": 566.1698113207547, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31640.0, "min": 15984.0, "max": 32563.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8712162830087603, "min": -1.0000000521540642, "max": 0.9533333048500396, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 42.689597867429256, "min": -31.99320164322853, "max": 51.47999846190214, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8712162830087603, "min": -1.0000000521540642, "max": 0.9533333048500396, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 42.689597867429256, "min": -31.99320164322853, "max": 51.47999846190214, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09578146394912382, "min": 0.09165765505814408, "max": 6.9449106473475695, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.693291733507067, "min": 4.630503593507456, "max": 111.11857035756111, "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": "1721916431", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721919612" }, "total": 3180.73370772, "count": 1, "self": 0.7947104579998268, "children": { "run_training.setup": { "total": 0.07077057200001491, "count": 1, "self": 0.07077057200001491 }, "TrainerController.start_learning": { "total": 3179.86822669, "count": 1, "self": 2.3857583149770107, "children": { "TrainerController._reset_env": { "total": 3.1439796650000176, "count": 1, "self": 3.1439796650000176 }, "TrainerController.advance": { "total": 3174.2534468930226, "count": 63283, "self": 2.524634227065235, "children": { "env_step": { "total": 2069.3605310120124, "count": 63283, "self": 1904.740085341946, "children": { "SubprocessEnvManager._take_step": { "total": 163.2051896600156, "count": 63283, "self": 7.3917117130922065, "children": { "TorchPolicy.evaluate": { "total": 155.8134779469234, "count": 62574, "self": 155.8134779469234 } } }, "workers": { "total": 1.4152560100507117, "count": 63283, "self": 0.0, "children": { "worker_root": { "total": 3172.3573158280037, "count": 63283, "is_parallel": true, "self": 1454.8350297329985, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005466948999981014, "count": 1, "is_parallel": true, "self": 0.00358252299980677, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018844260001742441, "count": 8, "is_parallel": true, "self": 0.0018844260001742441 } } }, "UnityEnvironment.step": { "total": 0.05730140000002848, "count": 1, "is_parallel": true, "self": 0.0007552509999868562, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005298600000287479, "count": 1, "is_parallel": true, "self": 0.0005298600000287479 }, "communicator.exchange": { "total": 0.054153686000006473, "count": 1, "is_parallel": true, "self": 0.054153686000006473 }, "steps_from_proto": { "total": 0.001862603000006402, "count": 1, "is_parallel": true, "self": 0.00039181000011012657, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014707929998962754, "count": 8, "is_parallel": true, "self": 0.0014707929998962754 } } } } } } }, "UnityEnvironment.step": { "total": 1717.5222860950053, "count": 63282, "is_parallel": true, "self": 52.566312589007794, "children": { "UnityEnvironment._generate_step_input": { "total": 32.14106916497167, "count": 63282, "is_parallel": true, "self": 32.14106916497167 }, "communicator.exchange": { "total": 1498.2908997040313, "count": 63282, "is_parallel": true, "self": 1498.2908997040313 }, "steps_from_proto": { "total": 134.5240046369944, "count": 63282, "is_parallel": true, "self": 29.237643085947695, "children": { "_process_rank_one_or_two_observation": { "total": 105.2863615510467, "count": 506256, "is_parallel": true, "self": 105.2863615510467 } } } } } } } } } } }, "trainer_advance": { "total": 1102.368281653945, "count": 63283, "self": 4.5428839849682845, "children": { "process_trajectory": { "total": 163.8804928939735, "count": 63283, "self": 163.5855752229736, "children": { "RLTrainer._checkpoint": { "total": 0.29491767099989374, "count": 2, "self": 0.29491767099989374 } } }, "_update_policy": { "total": 933.9449047750031, "count": 450, "self": 388.4577855530065, "children": { "TorchPPOOptimizer.update": { "total": 545.4871192219966, "count": 22851, "self": 545.4871192219966 } } } } } } }, "trainer_threads": { "total": 1.3660001059179194e-06, "count": 1, "self": 1.3660001059179194e-06 }, "TrainerController._save_models": { "total": 0.0850404510001681, "count": 1, "self": 0.0023008130001471727, "children": { "RLTrainer._checkpoint": { "total": 0.08273963800002093, "count": 1, "self": 0.08273963800002093 } } } } } } }