{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4866746962070465, "min": 0.4819784462451935, "max": 1.4704461097717285, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14475.65234375, "min": 14475.65234375, "max": 44607.453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4255790710449219, "min": -0.1660817712545395, "max": 0.483580619096756, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 112.77845001220703, "min": -39.36138153076172, "max": 129.599609375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.009613361209630966, "min": -0.009613361209630966, "max": 0.4051348865032196, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.5475406646728516, "min": -2.5475406646728516, "max": 96.0169677734375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07023399615995697, "min": 0.06478494070470334, "max": 0.0744606949231967, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9832759462393975, "min": 0.45733628309520513, "max": 1.0424497289247536, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013792137313603667, "min": 0.0007647788233143253, "max": 0.01483539521692716, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19308992239045134, "min": 0.010706903526400554, "max": 0.20769553303698024, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.629890313878567e-06, "min": 7.629890313878567e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010681846439429994, "min": 0.00010681846439429994, "max": 0.0036327121890960003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025432642857143, "min": 0.1025432642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356057000000002, "min": 1.3886848, "max": 2.610904, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002640721021428571, "min": 0.0002640721021428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036970094299999994, "min": 0.0036970094299999994, "max": 0.1211093096, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010788388550281525, "min": 0.010788388550281525, "max": 0.46336987614631653, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15103743970394135, "min": 0.15103743970394135, "max": 3.243589162826538, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 420.83561643835617, "min": 389.6625, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30721.0, "min": 15984.0, "max": 33115.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3815971946136818, "min": -1.0000000521540642, "max": 1.5290675501565676, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 99.4749980121851, "min": -29.14700174331665, "max": 113.19119822978973, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3815971946136818, "min": -1.0000000521540642, "max": 1.5290675501565676, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 99.4749980121851, "min": -29.14700174331665, "max": 113.19119822978973, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04753646299327051, "min": 0.04753646299327051, "max": 8.934927144087851, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4226253355154768, "min": 3.4226253355154768, "max": 142.95883430540562, "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": "1732984396", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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=PyramidsTraining --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1732987013" }, "total": 2617.1157349419996, "count": 1, "self": 0.5266976519997115, "children": { "run_training.setup": { "total": 0.06800029999976687, "count": 1, "self": 0.06800029999976687 }, "TrainerController.start_learning": { "total": 2616.52103699, "count": 1, "self": 1.985749643987674, "children": { "TrainerController._reset_env": { "total": 2.6431613049999214, "count": 1, "self": 2.6431613049999214 }, "TrainerController.advance": { "total": 2611.8042161170133, "count": 63664, "self": 1.9591416860143909, "children": { "env_step": { "total": 1841.454075376043, "count": 63664, "self": 1651.2710671001705, "children": { "SubprocessEnvManager._take_step": { "total": 189.0558243478995, "count": 63664, "self": 5.7667154839714385, "children": { "TorchPolicy.evaluate": { "total": 183.28910886392805, "count": 62558, "self": 183.28910886392805 } } }, "workers": { "total": 1.1271839279729647, "count": 63664, "self": 0.0, "children": { "worker_root": { "total": 2610.3318086820123, "count": 63664, "is_parallel": true, "self": 1106.3666766211027, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025634969997554435, "count": 1, "is_parallel": true, "self": 0.0008216629998969438, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017418339998584997, "count": 8, "is_parallel": true, "self": 0.0017418339998584997 } } }, "UnityEnvironment.step": { "total": 0.11687405500015302, "count": 1, "is_parallel": true, "self": 0.0007762019995425362, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005951360003564332, "count": 1, "is_parallel": true, "self": 0.0005951360003564332 }, "communicator.exchange": { "total": 0.11346911100008583, "count": 1, "is_parallel": true, "self": 0.11346911100008583 }, "steps_from_proto": { "total": 0.00203360600016822, "count": 1, "is_parallel": true, "self": 0.00044513300053949933, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015884729996287206, "count": 8, "is_parallel": true, "self": 0.0015884729996287206 } } } } } } }, "UnityEnvironment.step": { "total": 1503.9651320609096, "count": 63663, "is_parallel": true, "self": 40.22273428909784, "children": { "UnityEnvironment._generate_step_input": { "total": 27.219916052012195, "count": 63663, "is_parallel": true, "self": 27.219916052012195 }, "communicator.exchange": { "total": 1318.250295694967, "count": 63663, "is_parallel": true, "self": 1318.250295694967 }, "steps_from_proto": { "total": 118.27218602483254, "count": 63663, "is_parallel": true, "self": 25.872104360689264, "children": { "_process_rank_one_or_two_observation": { "total": 92.40008166414327, "count": 509304, "is_parallel": true, "self": 92.40008166414327 } } } } } } } } } } }, "trainer_advance": { "total": 768.390999054956, "count": 63664, "self": 3.5292332749422712, "children": { "process_trajectory": { "total": 152.5426576420141, "count": 63664, "self": 152.30593538701442, "children": { "RLTrainer._checkpoint": { "total": 0.2367222549996768, "count": 2, "self": 0.2367222549996768 } } }, "_update_policy": { "total": 612.3191081379996, "count": 452, "self": 343.44890062799277, "children": { "TorchPPOOptimizer.update": { "total": 268.8702075100068, "count": 22800, "self": 268.8702075100068 } } } } } } }, "trainer_threads": { "total": 9.739997040014714e-07, "count": 1, "self": 9.739997040014714e-07 }, "TrainerController._save_models": { "total": 0.0879089499994734, "count": 1, "self": 0.001435447999938333, "children": { "RLTrainer._checkpoint": { "total": 0.08647350199953507, "count": 1, "self": 0.08647350199953507 } } } } } } }