{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5814186334609985, "min": 0.5592879056930542, "max": 1.4764949083328247, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17554.19140625, "min": 16903.91796875, "max": 44790.94921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.17124579846858978, "min": -0.15393362939357758, "max": 0.17124579846858978, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 44.010169982910156, "min": -37.25193786621094, "max": 44.010169982910156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0039293221198022366, "min": 0.002365364693105221, "max": 0.2782208323478699, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.0098358392715454, "min": 0.5913411974906921, "max": 67.3294448852539, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06983583501818282, "min": 0.06491532899372159, "max": 0.07184738567705835, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9777016902545594, "min": 0.49804875389646064, "max": 1.0131324736992646, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011026238495080169, "min": 7.534382911759324e-05, "max": 0.011026238495080169, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15436733893112237, "min": 0.0010548136076463054, "max": 0.15436733893112237, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.747747417449997e-06, "min": 7.747747417449997e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010846846384429997, "min": 0.00010846846384429997, "max": 0.003635609888130099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258255000000001, "min": 0.10258255000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361557, "min": 1.3886848, "max": 2.6118699000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026799674499999995, "min": 0.00026799674499999995, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037519544299999996, "min": 0.0037519544299999996, "max": 0.12120580300999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011755081824958324, "min": 0.011755081824958324, "max": 0.38727813959121704, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.164571151137352, "min": 0.164571151137352, "max": 2.710947036743164, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 610.7254901960785, "min": 610.7254901960785, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31147.0, "min": 15984.0, "max": 32960.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7616313468007481, "min": -1.0000000521540642, "max": 0.7616313468007481, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 38.84319868683815, "min": -30.2422017082572, "max": 38.84319868683815, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7616313468007481, "min": -1.0000000521540642, "max": 0.7616313468007481, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 38.84319868683815, "min": -30.2422017082572, "max": 38.84319868683815, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07417967817380879, "min": 0.07417967817380879, "max": 7.205812143161893, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.783163586864248, "min": 3.752242462243885, "max": 115.29299429059029, "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": "1740590560", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740592824" }, "total": 2263.9589436379997, "count": 1, "self": 0.6407182250000005, "children": { "run_training.setup": { "total": 0.02191090299993448, "count": 1, "self": 0.02191090299993448 }, "TrainerController.start_learning": { "total": 2263.29631451, "count": 1, "self": 1.369886679069623, "children": { "TrainerController._reset_env": { "total": 2.2196713769999405, "count": 1, "self": 2.2196713769999405 }, "TrainerController.advance": { "total": 2259.61339118893, "count": 63351, "self": 1.4391257318325188, "children": { "env_step": { "total": 1554.8218773801045, "count": 63351, "self": 1393.6062844172634, "children": { "SubprocessEnvManager._take_step": { "total": 160.40866890790858, "count": 63351, "self": 4.898199881978599, "children": { "TorchPolicy.evaluate": { "total": 155.51046902592998, "count": 62551, "self": 155.51046902592998 } } }, "workers": { "total": 0.8069240549325514, "count": 63351, "self": 0.0, "children": { "worker_root": { "total": 2257.7677427810336, "count": 63351, "is_parallel": true, "self": 984.4785886900409, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025419069997951738, "count": 1, "is_parallel": true, "self": 0.000823137998850143, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017187690009450307, "count": 8, "is_parallel": true, "self": 0.0017187690009450307 } } }, "UnityEnvironment.step": { "total": 0.05474524500004918, "count": 1, "is_parallel": true, "self": 0.0005393360002017289, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000566190999961691, "count": 1, "is_parallel": true, "self": 0.000566190999961691 }, "communicator.exchange": { "total": 0.05190098399998533, "count": 1, "is_parallel": true, "self": 0.05190098399998533 }, "steps_from_proto": { "total": 0.0017387339999004325, "count": 1, "is_parallel": true, "self": 0.000383410999802436, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013553230000979966, "count": 8, "is_parallel": true, "self": 0.0013553230000979966 } } } } } } }, "UnityEnvironment.step": { "total": 1273.2891540909927, "count": 63350, "is_parallel": true, "self": 33.47225943584999, "children": { "UnityEnvironment._generate_step_input": { "total": 25.401316229050735, "count": 63350, "is_parallel": true, "self": 25.401316229050735 }, "communicator.exchange": { "total": 1110.042568701052, "count": 63350, "is_parallel": true, "self": 1110.042568701052 }, "steps_from_proto": { "total": 104.37300972503999, "count": 63350, "is_parallel": true, "self": 21.175193644151477, "children": { "_process_rank_one_or_two_observation": { "total": 83.19781608088851, "count": 506800, "is_parallel": true, "self": 83.19781608088851 } } } } } } } } } } }, "trainer_advance": { "total": 703.3523880769931, "count": 63351, "self": 2.6597976290722727, "children": { "process_trajectory": { "total": 135.0890862779138, "count": 63351, "self": 134.85044427991397, "children": { "RLTrainer._checkpoint": { "total": 0.2386419979998209, "count": 2, "self": 0.2386419979998209 } } }, "_update_policy": { "total": 565.603504170007, "count": 455, "self": 311.56091201296385, "children": { "TorchPPOOptimizer.update": { "total": 254.04259215704315, "count": 22746, "self": 254.04259215704315 } } } } } } }, "trainer_threads": { "total": 1.0320000001229346e-06, "count": 1, "self": 1.0320000001229346e-06 }, "TrainerController._save_models": { "total": 0.0933642330001021, "count": 1, "self": 0.0015217700001812773, "children": { "RLTrainer._checkpoint": { "total": 0.09184246299992083, "count": 1, "self": 0.09184246299992083 } } } } } } }