{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.49195191264152527, "min": 0.49195191264152527, "max": 1.4195449352264404, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14821.52734375, "min": 14821.52734375, "max": 43063.31640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6544671058654785, "min": -0.08916456252336502, "max": 0.6757876873016357, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 186.5231170654297, "min": -21.488658905029297, "max": 195.30264282226562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03394154831767082, "min": -0.0018346430733799934, "max": 0.5959321856498718, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.673341751098633, "min": -0.4971882700920105, "max": 141.23593139648438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0681995489721885, "min": 0.0637420393606936, "max": 0.07520342497474643, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9547936856106389, "min": 0.49694018122297173, "max": 1.0899919870725547, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01602361271146773, "min": 0.0004993987653167891, "max": 0.016892166276409715, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22433057796054826, "min": 0.003995190122534313, "max": 0.24360727770059992, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.416354670771424e-06, "min": 7.416354670771424e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010382896539079994, "min": 0.00010382896539079994, "max": 0.0035076608307798, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247208571428572, "min": 0.10247208571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346092000000001, "min": 1.3691136000000002, "max": 2.5724103000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002569613628571428, "min": 0.0002569613628571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003597459079999999, "min": 0.003597459079999999, "max": 0.11694509798, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012658745050430298, "min": 0.012508303858339787, "max": 0.6539335250854492, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17722243070602417, "min": 0.17511625587940216, "max": 4.5775346755981445, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 296.4141414141414, "min": 283.27884615384613, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29345.0, "min": 15984.0, "max": 32601.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6833777606788307, "min": -1.0000000521540642, "max": 1.6877207819483069, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 166.65439830720425, "min": -32.000001668930054, "max": 176.41439823806286, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6833777606788307, "min": -1.0000000521540642, "max": 1.6877207819483069, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 166.65439830720425, "min": -32.000001668930054, "max": 176.41439823806286, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03861586347465154, "min": 0.03709550110548402, "max": 13.777548976242542, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8229704839905025, "min": 3.8229704839905025, "max": 220.44078361988068, "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": "1684907383", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.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": "1684910898" }, "total": 3514.406738826, "count": 1, "self": 0.6414082569999664, "children": { "run_training.setup": { "total": 0.05702000400015095, "count": 1, "self": 0.05702000400015095 }, "TrainerController.start_learning": { "total": 3513.708310565, "count": 1, "self": 2.360263203674549, "children": { "TrainerController._reset_env": { "total": 1.1608714530002544, "count": 1, "self": 1.1608714530002544 }, "TrainerController.advance": { "total": 3510.0635492733263, "count": 64021, "self": 2.4131002231924867, "children": { "env_step": { "total": 2355.432417504998, "count": 64021, "self": 2214.8959060364014, "children": { "SubprocessEnvManager._take_step": { "total": 139.02446974079794, "count": 64021, "self": 6.8878794587444645, "children": { "TorchPolicy.evaluate": { "total": 132.13659028205348, "count": 62553, "self": 132.13659028205348 } } }, "workers": { "total": 1.5120417277985325, "count": 64021, "self": 0.0, "children": { "worker_root": { "total": 3506.3312222028126, "count": 64021, "is_parallel": true, "self": 1468.0180033490979, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0032430119999844464, "count": 1, "is_parallel": true, "self": 0.0010693670001273858, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021736449998570606, "count": 8, "is_parallel": true, "self": 0.0021736449998570606 } } }, "UnityEnvironment.step": { "total": 0.0737718850004967, "count": 1, "is_parallel": true, "self": 0.0007466240003850544, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006769210003767512, "count": 1, "is_parallel": true, "self": 0.0006769210003767512 }, "communicator.exchange": { "total": 0.0698184279999623, "count": 1, "is_parallel": true, "self": 0.0698184279999623 }, "steps_from_proto": { "total": 0.002529911999772594, "count": 1, "is_parallel": true, "self": 0.000523305999195145, "children": { "_process_rank_one_or_two_observation": { "total": 0.002006606000577449, "count": 8, "is_parallel": true, "self": 0.002006606000577449 } } } } } } }, "UnityEnvironment.step": { "total": 2038.3132188537147, "count": 64020, "is_parallel": true, "self": 46.454694812702655, "children": { "UnityEnvironment._generate_step_input": { "total": 26.422485297947787, "count": 64020, "is_parallel": true, "self": 26.422485297947787 }, "communicator.exchange": { "total": 1826.1315154360636, "count": 64020, "is_parallel": true, "self": 1826.1315154360636 }, "steps_from_proto": { "total": 139.30452330700064, "count": 64020, "is_parallel": true, "self": 29.973613045073762, "children": { "_process_rank_one_or_two_observation": { "total": 109.33091026192687, "count": 512160, "is_parallel": true, "self": 109.33091026192687 } } } } } } } } } } }, "trainer_advance": { "total": 1152.218031545136, "count": 64021, "self": 4.900510493889669, "children": { "process_trajectory": { "total": 148.43118380524902, "count": 64021, "self": 148.1136108012488, "children": { "RLTrainer._checkpoint": { "total": 0.3175730040002236, "count": 2, "self": 0.3175730040002236 } } }, "_update_policy": { "total": 998.8863372459973, "count": 448, "self": 420.6131185409622, "children": { "TorchPPOOptimizer.update": { "total": 578.2732187050351, "count": 22854, "self": 578.2732187050351 } } } } } } }, "trainer_threads": { "total": 1.4090001059230417e-06, "count": 1, "self": 1.4090001059230417e-06 }, "TrainerController._save_models": { "total": 0.12362522599869408, "count": 1, "self": 0.0015509079985349672, "children": { "RLTrainer._checkpoint": { "total": 0.12207431800015911, "count": 1, "self": 0.12207431800015911 } } } } } } }