{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5061929821968079, "min": 0.48148712515830994, "max": 1.4885462522506714, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15023.80859375, "min": 14614.09765625, "max": 45156.5390625, "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": 0.5278332233428955, "min": -0.21308866143226624, "max": 0.5278332233428955, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 146.73764038085938, "min": -50.50201416015625, "max": 146.73764038085938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.003276066156104207, "min": -0.03472806513309479, "max": 0.2081988900899887, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.9107463955879211, "min": -9.029296875, "max": 49.967735290527344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06773995052693257, "min": 0.06357601191917811, "max": 0.07300685882745753, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.948359307377056, "min": 0.5013870869228957, "max": 1.0583296912227522, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015690401983669115, "min": 0.0009223666860894551, "max": 0.01638506353407696, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2196656277713676, "min": 0.010820270607208991, "max": 0.24014115874403313, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.488268932514286e-06, "min": 7.488268932514286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001048357650552, "min": 0.0001048357650552, "max": 0.0035077385307538994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249605714285714, "min": 0.10249605714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349448, "min": 1.3886848, "max": 2.5692461000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002593561085714285, "min": 0.0002593561085714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036309855199999994, "min": 0.0036309855199999994, "max": 0.11694768538999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010861099697649479, "min": 0.010493587702512741, "max": 0.3524326980113983, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15205539762973785, "min": 0.15100853145122528, "max": 2.467028856277466, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 365.0506329113924, "min": 365.0506329113924, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28839.0, "min": 15984.0, "max": 33095.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5599599822424353, "min": -1.0000000521540642, "max": 1.5599599822424353, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 124.79679857939482, "min": -30.60700172185898, "max": 124.79679857939482, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5599599822424353, "min": -1.0000000521540642, "max": 1.5599599822424353, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 124.79679857939482, "min": -30.60700172185898, "max": 124.79679857939482, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04127381929720286, "min": 0.04127381929720286, "max": 7.008329352363944, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.301905543776229, "min": 3.2004510377300903, "max": 112.1332696378231, "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": "1710351359", "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 --force --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710354622" }, "total": 3263.265003032, "count": 1, "self": 1.051879433999602, "children": { "run_training.setup": { "total": 0.06876604400008546, "count": 1, "self": 0.06876604400008546 }, "TrainerController.start_learning": { "total": 3262.1443575540006, "count": 1, "self": 2.2762065079987224, "children": { "TrainerController._reset_env": { "total": 3.5661442230000375, "count": 1, "self": 3.5661442230000375 }, "TrainerController.advance": { "total": 3256.1492927900013, "count": 63563, "self": 2.573593744041773, "children": { "env_step": { "total": 2170.1512526920524, "count": 63563, "self": 2001.622638431134, "children": { "SubprocessEnvManager._take_step": { "total": 167.06037736197345, "count": 63563, "self": 7.492412818953198, "children": { "TorchPolicy.evaluate": { "total": 159.56796454302025, "count": 62543, "self": 159.56796454302025 } } }, "workers": { "total": 1.4682368989449515, "count": 63563, "self": 0.0, "children": { "worker_root": { "total": 3255.5260138370254, "count": 63563, "is_parallel": true, "self": 1439.8362128949761, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0072606720000294445, "count": 1, "is_parallel": true, "self": 0.004713802999731342, "children": { "_process_rank_one_or_two_observation": { "total": 0.002546869000298102, "count": 8, "is_parallel": true, "self": 0.002546869000298102 } } }, "UnityEnvironment.step": { "total": 0.07250100299984297, "count": 1, "is_parallel": true, "self": 0.0008006869998098409, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005106589999286371, "count": 1, "is_parallel": true, "self": 0.0005106589999286371 }, "communicator.exchange": { "total": 0.0690768700001172, "count": 1, "is_parallel": true, "self": 0.0690768700001172 }, "steps_from_proto": { "total": 0.002112786999987293, "count": 1, "is_parallel": true, "self": 0.00048062199994092225, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016321650000463706, "count": 8, "is_parallel": true, "self": 0.0016321650000463706 } } } } } } }, "UnityEnvironment.step": { "total": 1815.6898009420493, "count": 63562, "is_parallel": true, "self": 51.558596242046406, "children": { "UnityEnvironment._generate_step_input": { "total": 29.433843804048365, "count": 63562, "is_parallel": true, "self": 29.433843804048365 }, "communicator.exchange": { "total": 1597.0775824309783, "count": 63562, "is_parallel": true, "self": 1597.0775824309783 }, "steps_from_proto": { "total": 137.6197784649762, "count": 63562, "is_parallel": true, "self": 29.947599803848334, "children": { "_process_rank_one_or_two_observation": { "total": 107.67217866112787, "count": 508496, "is_parallel": true, "self": 107.67217866112787 } } } } } } } } } } }, "trainer_advance": { "total": 1083.4244463539071, "count": 63563, "self": 4.475897161953071, "children": { "process_trajectory": { "total": 169.00933926895095, "count": 63563, "self": 168.6893997759512, "children": { "RLTrainer._checkpoint": { "total": 0.3199394929997652, "count": 2, "self": 0.3199394929997652 } } }, "_update_policy": { "total": 909.9392099230031, "count": 447, "self": 370.51468735305457, "children": { "TorchPPOOptimizer.update": { "total": 539.4245225699485, "count": 22803, "self": 539.4245225699485 } } } } } } }, "trainer_threads": { "total": 1.3010003385716118e-06, "count": 1, "self": 1.3010003385716118e-06 }, "TrainerController._save_models": { "total": 0.15271273200050928, "count": 1, "self": 0.006411060000573343, "children": { "RLTrainer._checkpoint": { "total": 0.14630167199993593, "count": 1, "self": 0.14630167199993593 } } } } } } }