{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43518364429473877, "min": 0.43518364429473877, "max": 1.4008835554122925, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13097.287109375, "min": 13097.287109375, "max": 42497.203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6261143088340759, "min": -0.07144560664892197, "max": 0.6623799800872803, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 179.06869506835938, "min": -17.21839141845703, "max": 189.440673828125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022230735048651695, "min": -0.07831678539514542, "max": 0.49758803844451904, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.357990264892578, "min": -19.970779418945312, "max": 117.9283676147461, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06751873690081041, "min": 0.06463483799606332, "max": 0.0752032546532722, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0127810535121562, "min": 0.5062746874367198, "max": 1.0692180487676524, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014756779075414552, "min": 0.0013953093179874855, "max": 0.016469633328337556, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22135168613121828, "min": 0.019362754656232748, "max": 0.23057486659672577, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.519157493646671e-06, "min": 7.519157493646671e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011278736240470007, "min": 0.00011278736240470007, "max": 0.003633582788805799, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250635333333333, "min": 0.10250635333333333, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375953, "min": 1.3886848, "max": 2.6111941999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002603846980000002, "min": 0.0002603846980000002, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003905770470000003, "min": 0.003905770470000003, "max": 0.12113830058, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013969703577458858, "min": 0.013969703577458858, "max": 0.6064023375511169, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2095455527305603, "min": 0.1996900886297226, "max": 4.244816303253174, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 297.1326530612245, "min": 288.95327102803736, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29119.0, "min": 15984.0, "max": 33373.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6416244739476515, "min": -1.0000000521540642, "max": 1.6777312988885726, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 160.87919844686985, "min": -29.404801733791828, "max": 175.07899793982506, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6416244739476515, "min": -1.0000000521540642, "max": 1.6777312988885726, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 160.87919844686985, "min": -29.404801733791828, "max": 175.07899793982506, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.042875321748267324, "min": 0.042875321748267324, "max": 13.174597572535276, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.201781531330198, "min": 4.201781531330198, "max": 210.79356116056442, "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": "1678517802", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.29.0", "mlagents_envs_version": "0.29.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678520316" }, "total": 2514.3380332139996, "count": 1, "self": 0.6724436009999408, "children": { "run_training.setup": { "total": 0.12496005599950877, "count": 1, "self": 0.12496005599950877 }, "TrainerController.start_learning": { "total": 2513.540629557, "count": 1, "self": 1.5455442210659385, "children": { "TrainerController._reset_env": { "total": 6.757858976000534, "count": 1, "self": 6.757858976000534 }, "TrainerController.advance": { "total": 2505.1529272579337, "count": 64028, "self": 1.6249412708812088, "children": { "env_step": { "total": 1647.9095378310503, "count": 64028, "self": 1515.5989324909842, "children": { "SubprocessEnvManager._take_step": { "total": 131.39720295402367, "count": 64028, "self": 6.590383829986422, "children": { "TorchPolicy.evaluate": { "total": 124.80681912403725, "count": 62561, "self": 41.04265436314745, "children": { "TorchPolicy.sample_actions": { "total": 83.7641647608898, "count": 62561, "self": 83.7641647608898 } } } } }, "workers": { "total": 0.913402386042435, "count": 64028, "self": 0.0, "children": { "worker_root": { "total": 2507.9848587318174, "count": 64028, "is_parallel": true, "self": 1116.5606273633903, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001878887000202667, "count": 1, "is_parallel": true, "self": 0.0007088290003594011, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011700579998432659, "count": 8, "is_parallel": true, "self": 0.0011700579998432659 } } }, "UnityEnvironment.step": { "total": 0.10364535700045963, "count": 1, "is_parallel": true, "self": 0.0005326320015228703, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048392999997304287, "count": 1, "is_parallel": true, "self": 0.00048392999997304287 }, "communicator.exchange": { "total": 0.1008737829997699, "count": 1, "is_parallel": true, "self": 0.1008737829997699 }, "steps_from_proto": { "total": 0.0017550119991938118, "count": 1, "is_parallel": true, "self": 0.00041607699949963717, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013389349996941746, "count": 8, "is_parallel": true, "self": 0.0013389349996941746 } } } } } } }, "UnityEnvironment.step": { "total": 1391.4242313684272, "count": 64027, "is_parallel": true, "self": 31.564497749066504, "children": { "UnityEnvironment._generate_step_input": { "total": 22.458877300233326, "count": 64027, "is_parallel": true, "self": 22.458877300233326 }, "communicator.exchange": { "total": 1240.6487317851634, "count": 64027, "is_parallel": true, "self": 1240.6487317851634 }, "steps_from_proto": { "total": 96.75212453396398, "count": 64027, "is_parallel": true, "self": 22.838512297434136, "children": { "_process_rank_one_or_two_observation": { "total": 73.91361223652984, "count": 512216, "is_parallel": true, "self": 73.91361223652984 } } } } } } } } } } }, "trainer_advance": { "total": 855.6184481560022, "count": 64028, "self": 3.008347457097443, "children": { "process_trajectory": { "total": 188.74315739190297, "count": 64028, "self": 188.54180956590153, "children": { "RLTrainer._checkpoint": { "total": 0.20134782600143808, "count": 2, "self": 0.20134782600143808 } } }, "_update_policy": { "total": 663.8669433070017, "count": 456, "self": 264.6856807590075, "children": { "TorchPPOOptimizer.update": { "total": 399.18126254799427, "count": 22764, "self": 399.18126254799427 } } } } } } }, "trainer_threads": { "total": 1.1499996617203578e-06, "count": 1, "self": 1.1499996617203578e-06 }, "TrainerController._save_models": { "total": 0.08429795200027002, "count": 1, "self": 0.0013486190000548959, "children": { "RLTrainer._checkpoint": { "total": 0.08294933300021512, "count": 1, "self": 0.08294933300021512 } } } } } } }