{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2940797507762909, "min": 0.29177945852279663, "max": 1.5266907215118408, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8704.7607421875, "min": 8704.7607421875, "max": 46313.69140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5738489627838135, "min": -0.1804431676864624, "max": 0.6163069605827332, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 161.82540893554688, "min": -42.76502990722656, "max": 174.4148712158203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010815862566232681, "min": -0.015650028362870216, "max": 0.22419953346252441, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.0500731468200684, "min": -4.428957939147949, "max": 54.03208923339844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06780801963500886, "min": 0.06555721167934146, "max": 0.0749624230049362, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.017120294525133, "min": 0.5044945766376572, "max": 1.0534422545883275, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014588954404462128, "min": 0.0008508402200227301, "max": 0.016877641807941327, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21883431606693193, "min": 0.008508402200227302, "max": 0.2362869853111786, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.524897491733334e-06, "min": 7.524897491733334e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011287346237600001, "min": 0.00011287346237600001, "max": 0.0035073320308893997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250826666666667, "min": 0.10250826666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.537624, "min": 1.3886848, "max": 2.5691106, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002605758400000001, "min": 0.0002605758400000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039086376000000015, "min": 0.0039086376000000015, "max": 0.11693414894000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015421492978930473, "min": 0.015421492978930473, "max": 0.4567631185054779, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23132239282131195, "min": 0.2239353060722351, "max": 3.1973419189453125, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 326.8404255319149, "min": 319.3404255319149, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30723.0, "min": 15984.0, "max": 32963.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.630333312256362, "min": -1.0000000521540642, "max": 1.6567612795099136, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 151.62099803984165, "min": -31.99920167028904, "max": 154.07879899442196, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.630333312256362, "min": -1.0000000521540642, "max": 1.6567612795099136, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 151.62099803984165, "min": -31.99920167028904, "max": 154.07879899442196, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05173430486922703, "min": 0.05173430486922703, "max": 8.840237027965486, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.811290352838114, "min": 4.707263820106164, "max": 141.44379244744778, "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": "1752183752", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752185970" }, "total": 2217.8136008310003, "count": 1, "self": 0.6113388430003397, "children": { "run_training.setup": { "total": 0.021933667000041623, "count": 1, "self": 0.021933667000041623 }, "TrainerController.start_learning": { "total": 2217.1803283209997, "count": 1, "self": 1.3017846129901045, "children": { "TrainerController._reset_env": { "total": 3.20038402900002, "count": 1, "self": 3.20038402900002 }, "TrainerController.advance": { "total": 2212.5938138870097, "count": 63927, "self": 1.4012302340447604, "children": { "env_step": { "total": 1551.2036206459402, "count": 63927, "self": 1402.9065426639363, "children": { "SubprocessEnvManager._take_step": { "total": 147.51713223103047, "count": 63927, "self": 4.527033846041718, "children": { "TorchPolicy.evaluate": { "total": 142.99009838498876, "count": 62569, "self": 142.99009838498876 } } }, "workers": { "total": 0.7799457509732974, "count": 63927, "self": 0.0, "children": { "worker_root": { "total": 2212.0106330240365, "count": 63927, "is_parallel": true, "self": 920.6861952390079, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005082674000050247, "count": 1, "is_parallel": true, "self": 0.003551874000152111, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015307999998981359, "count": 8, "is_parallel": true, "self": 0.0015307999998981359 } } }, "UnityEnvironment.step": { "total": 0.10255239499997515, "count": 1, "is_parallel": true, "self": 0.0005652109999800814, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004415379999613833, "count": 1, "is_parallel": true, "self": 0.0004415379999613833 }, "communicator.exchange": { "total": 0.0997881200000279, "count": 1, "is_parallel": true, "self": 0.0997881200000279 }, "steps_from_proto": { "total": 0.0017575260000057824, "count": 1, "is_parallel": true, "self": 0.0003621160000761847, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013954099999295977, "count": 8, "is_parallel": true, "self": 0.0013954099999295977 } } } } } } }, "UnityEnvironment.step": { "total": 1291.3244377850285, "count": 63926, "is_parallel": true, "self": 32.3906772240407, "children": { "UnityEnvironment._generate_step_input": { "total": 22.91195796497334, "count": 63926, "is_parallel": true, "self": 22.91195796497334 }, "communicator.exchange": { "total": 1139.8625725100064, "count": 63926, "is_parallel": true, "self": 1139.8625725100064 }, "steps_from_proto": { "total": 96.15923008600811, "count": 63926, "is_parallel": true, "self": 19.080573586083517, "children": { "_process_rank_one_or_two_observation": { "total": 77.07865649992459, "count": 511408, "is_parallel": true, "self": 77.07865649992459 } } } } } } } } } } }, "trainer_advance": { "total": 659.9889630070247, "count": 63927, "self": 2.5177483249825627, "children": { "process_trajectory": { "total": 125.05152368904226, "count": 63927, "self": 124.76706515004219, "children": { "RLTrainer._checkpoint": { "total": 0.28445853900007023, "count": 2, "self": 0.28445853900007023 } } }, "_update_policy": { "total": 532.4196909929999, "count": 448, "self": 299.0217156079895, "children": { "TorchPPOOptimizer.update": { "total": 233.3979753850104, "count": 22818, "self": 233.3979753850104 } } } } } } }, "trainer_threads": { "total": 9.66999778029276e-07, "count": 1, "self": 9.66999778029276e-07 }, "TrainerController._save_models": { "total": 0.08434482500024387, "count": 1, "self": 0.0012525719998848217, "children": { "RLTrainer._checkpoint": { "total": 0.08309225300035905, "count": 1, "self": 0.08309225300035905 } } } } } } }