{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42266392707824707, "min": 0.42266392707824707, "max": 1.443179726600647, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12673.1552734375, "min": 12673.1552734375, "max": 43780.30078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989979.0, "min": 29952.0, "max": 989979.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989979.0, "min": 29952.0, "max": 989979.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5730925798416138, "min": -0.11577948182821274, "max": 0.5989294052124023, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 158.74664306640625, "min": -27.902854919433594, "max": 163.50772094726562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013314775191247463, "min": 0.00035554912756197155, "max": 0.4095391035079956, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.688192844390869, "min": 0.09848710894584656, "max": 97.0607681274414, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06756139894436855, "min": 0.06358663828342244, "max": 0.07697009513006581, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0134209841655282, "min": 0.5206497553080298, "max": 1.0775813318209213, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015114409633260831, "min": 0.0001371319985062773, "max": 0.015114409633260831, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22671614449891248, "min": 0.001782715980581605, "max": 0.22671614449891248, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.490697503133333e-06, "min": 7.490697503133333e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000112360462547, "min": 0.000112360462547, "max": 0.003507207230931, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249686666666667, "min": 0.10249686666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374530000000002, "min": 1.3886848, "max": 2.569069, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025943698, "min": 0.00025943698, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038915547, "min": 0.0038915547, "max": 0.11692999310000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010400055907666683, "min": 0.010400055907666683, "max": 0.3796156346797943, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15600083768367767, "min": 0.1540941298007965, "max": 2.6573095321655273, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 349.685393258427, "min": 339.3, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31122.0, "min": 15984.0, "max": 32689.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.605361782265513, "min": -1.0000000521540642, "max": 1.6162377566927009, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 142.87719862163067, "min": -31.99320164322853, "max": 145.46139810234308, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.605361782265513, "min": -1.0000000521540642, "max": 1.6162377566927009, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 142.87719862163067, "min": -31.99320164322853, "max": 145.46139810234308, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03784648474963811, "min": 0.03784648474963811, "max": 7.212618724443018, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3683371427177917, "min": 3.267331414623186, "max": 115.4018995910883, "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": "1705882665", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705884842" }, "total": 2177.2260012920005, "count": 1, "self": 0.4885462490001373, "children": { "run_training.setup": { "total": 0.04600044500011791, "count": 1, "self": 0.04600044500011791 }, "TrainerController.start_learning": { "total": 2176.6914545980003, "count": 1, "self": 1.277903346076073, "children": { "TrainerController._reset_env": { "total": 2.169951745000162, "count": 1, "self": 2.169951745000162 }, "TrainerController.advance": { "total": 2173.160050772924, "count": 63839, "self": 1.3939229869884002, "children": { "env_step": { "total": 1542.3998821069677, "count": 63839, "self": 1418.4534707059347, "children": { "SubprocessEnvManager._take_step": { "total": 123.1663279670679, "count": 63839, "self": 4.6531801529395125, "children": { "TorchPolicy.evaluate": { "total": 118.51314781412839, "count": 62565, "self": 118.51314781412839 } } }, "workers": { "total": 0.7800834339650464, "count": 63839, "self": 0.0, "children": { "worker_root": { "total": 2171.8419606359757, "count": 63839, "is_parallel": true, "self": 867.0214421700016, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021039120001660194, "count": 1, "is_parallel": true, "self": 0.0007511249996241531, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013527870005418663, "count": 8, "is_parallel": true, "self": 0.0013527870005418663 } } }, "UnityEnvironment.step": { "total": 0.05315029700022933, "count": 1, "is_parallel": true, "self": 0.0006730290001542016, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004951890000484127, "count": 1, "is_parallel": true, "self": 0.0004951890000484127 }, "communicator.exchange": { "total": 0.05010955900024783, "count": 1, "is_parallel": true, "self": 0.05010955900024783 }, "steps_from_proto": { "total": 0.0018725199997788877, "count": 1, "is_parallel": true, "self": 0.00039507499923274736, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014774450005461404, "count": 8, "is_parallel": true, "self": 0.0014774450005461404 } } } } } } }, "UnityEnvironment.step": { "total": 1304.8205184659741, "count": 63838, "is_parallel": true, "self": 34.420583480991354, "children": { "UnityEnvironment._generate_step_input": { "total": 24.15611767095743, "count": 63838, "is_parallel": true, "self": 24.15611767095743 }, "communicator.exchange": { "total": 1149.7828382370044, "count": 63838, "is_parallel": true, "self": 1149.7828382370044 }, "steps_from_proto": { "total": 96.46097907702097, "count": 63838, "is_parallel": true, "self": 18.912602694328598, "children": { "_process_rank_one_or_two_observation": { "total": 77.54837638269237, "count": 510704, "is_parallel": true, "self": 77.54837638269237 } } } } } } } } } } }, "trainer_advance": { "total": 629.366245678968, "count": 63839, "self": 2.5870246878544094, "children": { "process_trajectory": { "total": 123.3675563301149, "count": 63839, "self": 123.1872078301144, "children": { "RLTrainer._checkpoint": { "total": 0.18034850000049119, "count": 2, "self": 0.18034850000049119 } } }, "_update_policy": { "total": 503.41166466099867, "count": 448, "self": 300.9599636159064, "children": { "TorchPPOOptimizer.update": { "total": 202.45170104509225, "count": 22797, "self": 202.45170104509225 } } } } } } }, "trainer_threads": { "total": 1.1990005077677779e-06, "count": 1, "self": 1.1990005077677779e-06 }, "TrainerController._save_models": { "total": 0.08354753499952494, "count": 1, "self": 0.001381265999043535, "children": { "RLTrainer._checkpoint": { "total": 0.0821662690004814, "count": 1, "self": 0.0821662690004814 } } } } } } }