{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34154579043388367, "min": 0.32417991757392883, "max": 1.4215493202209473, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10202.65625, "min": 9849.8828125, "max": 43124.12109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989949.0, "min": 29952.0, "max": 989949.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989949.0, "min": 29952.0, "max": 989949.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6200006604194641, "min": -0.10368364304304123, "max": 0.6200006604194641, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.7001953125, "min": -24.98775863647461, "max": 176.7001953125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0031483278144150972, "min": -0.018381230533123016, "max": 0.3371911942958832, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.8972734212875366, "min": -5.201888084411621, "max": 79.91431427001953, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06980908580382156, "min": 0.06637119996081596, "max": 0.07280109544209315, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9773272012535018, "min": 0.4995243839443535, "max": 1.0920164316313972, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014992882159680853, "min": 0.00024052776629044913, "max": 0.016848503886516226, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20990035023553194, "min": 0.0028863331954853896, "max": 0.23587905441122717, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.62136174529286e-06, "min": 7.62136174529286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010669906443410004, "min": 0.00010669906443410004, "max": 0.003507299030900399, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254042142857142, "min": 0.10254042142857142, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355658999999998, "min": 1.3886848, "max": 2.5690996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026378810071428586, "min": 0.00026378810071428586, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003693033410000002, "min": 0.003693033410000002, "max": 0.11693305004, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011995785869657993, "min": 0.011863996274769306, "max": 0.4961375296115875, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16794100403785706, "min": 0.16609594225883484, "max": 3.4729626178741455, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 292.69607843137254, "min": 292.69607843137254, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29855.0, "min": 15984.0, "max": 32283.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6484627271545869, "min": -1.0000000521540642, "max": 1.6688367121529823, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 168.14319816976786, "min": -31.995601654052734, "max": 168.14319816976786, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6484627271545869, "min": -1.0000000521540642, "max": 1.6688367121529823, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 168.14319816976786, "min": -31.995601654052734, "max": 168.14319816976786, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03665336981251968, "min": 0.03665336981251968, "max": 10.872184567153454, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7386437208770076, "min": 3.628451132331975, "max": 173.95495307445526, "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": "1699606759", "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 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699609015" }, "total": 2255.537892632, "count": 1, "self": 0.492602352999711, "children": { "run_training.setup": { "total": 0.07962301399999205, "count": 1, "self": 0.07962301399999205 }, "TrainerController.start_learning": { "total": 2254.9656672650003, "count": 1, "self": 1.2512374000102682, "children": { "TrainerController._reset_env": { "total": 2.039493589999992, "count": 1, "self": 2.039493589999992 }, "TrainerController.advance": { "total": 2251.6114051559907, "count": 63952, "self": 1.3239888730331586, "children": { "env_step": { "total": 1470.0474848769745, "count": 63952, "self": 1376.1389312879635, "children": { "SubprocessEnvManager._take_step": { "total": 93.15112457699675, "count": 63952, "self": 4.284842827996286, "children": { "TorchPolicy.evaluate": { "total": 88.86628174900046, "count": 62557, "self": 88.86628174900046 } } }, "workers": { "total": 0.7574290120143559, "count": 63952, "self": 0.0, "children": { "worker_root": { "total": 2251.6639401619686, "count": 63952, "is_parallel": true, "self": 981.0436058319599, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00952003500000842, "count": 1, "is_parallel": true, "self": 0.007386776000032569, "children": { "_process_rank_one_or_two_observation": { "total": 0.002133258999975851, "count": 8, "is_parallel": true, "self": 0.002133258999975851 } } }, "UnityEnvironment.step": { "total": 0.07401524899999856, "count": 1, "is_parallel": true, "self": 0.0005591289999955507, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047041499999522784, "count": 1, "is_parallel": true, "self": 0.00047041499999522784 }, "communicator.exchange": { "total": 0.07139871300000777, "count": 1, "is_parallel": true, "self": 0.07139871300000777 }, "steps_from_proto": { "total": 0.0015869920000000093, "count": 1, "is_parallel": true, "self": 0.0003462689999906843, "children": { "_process_rank_one_or_two_observation": { "total": 0.001240723000009325, "count": 8, "is_parallel": true, "self": 0.001240723000009325 } } } } } } }, "UnityEnvironment.step": { "total": 1270.6203343300087, "count": 63951, "is_parallel": true, "self": 32.938889550006934, "children": { "UnityEnvironment._generate_step_input": { "total": 18.405153923988948, "count": 63951, "is_parallel": true, "self": 18.405153923988948 }, "communicator.exchange": { "total": 1125.6860245640369, "count": 63951, "is_parallel": true, "self": 1125.6860245640369 }, "steps_from_proto": { "total": 93.59026629197592, "count": 63951, "is_parallel": true, "self": 18.35641417802681, "children": { "_process_rank_one_or_two_observation": { "total": 75.23385211394911, "count": 511608, "is_parallel": true, "self": 75.23385211394911 } } } } } } } } } } }, "trainer_advance": { "total": 780.2399314059832, "count": 63952, "self": 2.4178023940082767, "children": { "process_trajectory": { "total": 116.52973652497539, "count": 63952, "self": 116.33130163097562, "children": { "RLTrainer._checkpoint": { "total": 0.19843489399977443, "count": 2, "self": 0.19843489399977443 } } }, "_update_policy": { "total": 661.2923924869995, "count": 449, "self": 279.5685566459839, "children": { "TorchPPOOptimizer.update": { "total": 381.72383584101556, "count": 22737, "self": 381.72383584101556 } } } } } } }, "trainer_threads": { "total": 9.689997568784747e-07, "count": 1, "self": 9.689997568784747e-07 }, "TrainerController._save_models": { "total": 0.06353014999967854, "count": 1, "self": 0.0011650989999907324, "children": { "RLTrainer._checkpoint": { "total": 0.06236505099968781, "count": 1, "self": 0.06236505099968781 } } } } } } }