{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.49696850776672363, "min": 0.49696850776672363, "max": 1.4081650972366333, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14901.103515625, "min": 14901.103515625, "max": 42718.09765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.41353651881217957, "min": -0.11066388338804245, "max": 0.4502978026866913, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 110.82778930664062, "min": -26.66999626159668, "max": 122.48100280761719, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.002935063326731324, "min": -0.01595137268304825, "max": 0.5726882219314575, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.786596953868866, "min": -4.019745826721191, "max": 135.72711181640625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06554523098886766, "min": 0.06518754058569257, "max": 0.07485660904604333, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9176332338441473, "min": 0.5178103298848715, "max": 1.0494812746862106, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014787017050929578, "min": 0.0004327237056574881, "max": 0.016972040224027807, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20701823871301409, "min": 0.005192684467889857, "max": 0.23760856313638928, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.670411728942855e-06, "min": 7.670411728942855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010738576420519998, "min": 0.00010738576420519998, "max": 0.0033310932896355996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255677142857145, "min": 0.10255677142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357948000000003, "min": 1.3886848, "max": 2.4431847999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002654214657142857, "min": 0.0002654214657142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00371590052, "min": 0.00371590052, "max": 0.11104540355999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00718091893941164, "min": 0.00718091893941164, "max": 0.5711057782173157, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10053286701440811, "min": 0.10053286701440811, "max": 3.9977405071258545, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 448.6714285714286, "min": 379.1333333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31407.0, "min": 15984.0, "max": 32910.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3853246083726054, "min": -1.0000000521540642, "max": 1.5941866394877433, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 95.58739797770977, "min": -30.415001675486565, "max": 119.56399796158075, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3853246083726054, "min": -1.0000000521540642, "max": 1.5941866394877433, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 95.58739797770977, "min": -30.415001675486565, "max": 119.56399796158075, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03307373915837767, "min": 0.031789679408878634, "max": 12.326904576271772, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2820880019280594, "min": 2.2820880019280594, "max": 197.23047322034836, "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": "1692259243", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1692262095" }, "total": 2851.622209957, "count": 1, "self": 0.5414843069997914, "children": { "run_training.setup": { "total": 0.04826297400001067, "count": 1, "self": 0.04826297400001067 }, "TrainerController.start_learning": { "total": 2851.0324626760003, "count": 1, "self": 2.099993585935863, "children": { "TrainerController._reset_env": { "total": 5.999311329000022, "count": 1, "self": 5.999311329000022 }, "TrainerController.advance": { "total": 2842.8192059720645, "count": 63655, "self": 2.32555538799852, "children": { "env_step": { "total": 2071.0581755320277, "count": 63655, "self": 1909.1592903150497, "children": { "SubprocessEnvManager._take_step": { "total": 160.5613945229868, "count": 63655, "self": 6.6033532399659975, "children": { "TorchPolicy.evaluate": { "total": 153.9580412830208, "count": 62556, "self": 153.9580412830208 } } }, "workers": { "total": 1.3374906939911284, "count": 63655, "self": 0.0, "children": { "worker_root": { "total": 2843.4388888310273, "count": 63655, "is_parallel": true, "self": 1102.4766411729968, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008791168000016114, "count": 1, "is_parallel": true, "self": 0.006183483999961936, "children": { "_process_rank_one_or_two_observation": { "total": 0.002607684000054178, "count": 8, "is_parallel": true, "self": 0.002607684000054178 } } }, "UnityEnvironment.step": { "total": 0.05979317000003448, "count": 1, "is_parallel": true, "self": 0.0007414430000949324, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005974029999720187, "count": 1, "is_parallel": true, "self": 0.0005974029999720187 }, "communicator.exchange": { "total": 0.056023148000008405, "count": 1, "is_parallel": true, "self": 0.056023148000008405 }, "steps_from_proto": { "total": 0.002431175999959123, "count": 1, "is_parallel": true, "self": 0.00046840100003464613, "children": { "_process_rank_one_or_two_observation": { "total": 0.001962774999924477, "count": 8, "is_parallel": true, "self": 0.001962774999924477 } } } } } } }, "UnityEnvironment.step": { "total": 1740.9622476580305, "count": 63654, "is_parallel": true, "self": 45.647660876142936, "children": { "UnityEnvironment._generate_step_input": { "total": 30.185809399966047, "count": 63654, "is_parallel": true, "self": 30.185809399966047 }, "communicator.exchange": { "total": 1524.5041797599793, "count": 63654, "is_parallel": true, "self": 1524.5041797599793 }, "steps_from_proto": { "total": 140.62459762194226, "count": 63654, "is_parallel": true, "self": 29.268426549997628, "children": { "_process_rank_one_or_two_observation": { "total": 111.35617107194463, "count": 509232, "is_parallel": true, "self": 111.35617107194463 } } } } } } } } } } }, "trainer_advance": { "total": 769.4354750520382, "count": 63655, "self": 4.156754031018977, "children": { "process_trajectory": { "total": 139.59140136401396, "count": 63655, "self": 139.3344362590139, "children": { "RLTrainer._checkpoint": { "total": 0.256965105000063, "count": 2, "self": 0.256965105000063 } } }, "_update_policy": { "total": 625.6873196570052, "count": 449, "self": 404.4704455540059, "children": { "TorchPPOOptimizer.update": { "total": 221.21687410299933, "count": 22821, "self": 221.21687410299933 } } } } } } }, "trainer_threads": { "total": 1.216999862663215e-06, "count": 1, "self": 1.216999862663215e-06 }, "TrainerController._save_models": { "total": 0.11395057199979419, "count": 1, "self": 0.0017667850001998886, "children": { "RLTrainer._checkpoint": { "total": 0.1121837869995943, "count": 1, "self": 0.1121837869995943 } } } } } } }