{ "name": "root", "gauges": { "BigWallJump.Policy.Entropy.mean": { "value": 0.9725682139396667, "min": 0.9625186920166016, "max": 3.9519944190979004, "count": 1000 }, "BigWallJump.Policy.Entropy.sum": { "value": 19416.3515625, "min": 19233.048828125, "max": 82067.1171875, "count": 1000 }, "BigWallJump.Environment.EpisodeLength.mean": { "value": 24.652564102564103, "min": 24.180100755667507, "max": 360.2857142857143, "count": 1000 }, "BigWallJump.Environment.EpisodeLength.sum": { "value": 19229.0, "min": 17869.0, "max": 22004.0, "count": 1000 }, "BigWallJump.Step.mean": { "value": 19999998.0, "min": 19986.0, "max": 19999998.0, "count": 1000 }, "BigWallJump.Step.sum": { "value": 19999998.0, "min": 19986.0, "max": 19999998.0, "count": 1000 }, "BigWallJump.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8230504989624023, "min": -0.5544101595878601, "max": 0.8362411856651306, "count": 1000 }, "BigWallJump.Policy.ExtrinsicValueEstimate.sum": { "value": 641.9793701171875, "min": -146.78138732910156, "max": 659.5391235351562, "count": 1000 }, "BigWallJump.Environment.CumulativeReward.mean": { "value": 0.8793814066128853, "min": -1.2468177382446204, "max": 0.9177374817593565, "count": 1000 }, "BigWallJump.Environment.CumulativeReward.sum": { "value": 685.9174971580505, "min": -337.0195025871508, "max": 719.9999975562096, "count": 1000 }, "BigWallJump.Policy.ExtrinsicReward.mean": { "value": 0.8793814066128853, "min": -1.2468177382446204, "max": 0.9177374817593565, "count": 1000 }, "BigWallJump.Policy.ExtrinsicReward.sum": { "value": 685.9174971580505, "min": -337.0195025871508, "max": 719.9999975562096, "count": 1000 }, "BigWallJump.Losses.PolicyLoss.mean": { "value": 0.017277905321680005, "min": 0.013837956769081453, "max": 0.03131256672592523, "count": 1000 }, "BigWallJump.Losses.PolicyLoss.sum": { "value": 0.08638952660840003, "min": 0.06026011286303401, "max": 0.15406981386089075, "count": 1000 }, "BigWallJump.Losses.ValueLoss.mean": { "value": 0.02471310798233996, "min": 0.002555308794399025, "max": 0.08699909243732691, "count": 1000 }, "BigWallJump.Losses.ValueLoss.sum": { "value": 0.1235655399116998, "min": 0.0102212351775961, "max": 0.43499546218663454, "count": 1000 }, "BigWallJump.Policy.LearningRate.mean": { "value": 1.7335894224700115e-07, "min": 1.7335894224700115e-07, "max": 0.0002998448963017012, "count": 1000 }, "BigWallJump.Policy.LearningRate.sum": { "value": 8.667947112350057e-07, "min": 8.667947112350057e-07, "max": 0.001497824085725305, "count": 1000 }, "BigWallJump.Policy.Epsilon.mean": { "value": 0.100057753, "min": 0.100057753, "max": 0.19994829875000003, "count": 1000 }, "BigWallJump.Policy.Epsilon.sum": { "value": 0.500288765, "min": 0.400600675, "max": 0.999274695, "count": 1000 }, "BigWallJump.Policy.Beta.mean": { "value": 1.2881874700000022e-05, "min": 1.2881874700000022e-05, "max": 0.004997420107625, "count": 1000 }, "BigWallJump.Policy.Beta.sum": { "value": 6.44093735000001e-05, "min": 6.44093735000001e-05, "max": 0.024963807280500003, "count": 1000 }, "BigWallJump.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "BigWallJump.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SmallWallJump.Policy.Entropy.mean": { "value": 1.1432201862335205, "min": 1.127864122390747, "max": 3.9578561782836914, "count": 277 }, "SmallWallJump.Policy.Entropy.sum": { "value": 22802.669921875, "min": 22546.00390625, "max": 80419.6796875, "count": 277 }, "SmallWallJump.Environment.EpisodeLength.mean": { "value": 14.281130634071811, "min": 13.952914798206278, "max": 78.04247104247104, "count": 277 }, "SmallWallJump.Environment.EpisodeLength.sum": { "value": 18694.0, "min": 18662.0, "max": 20213.0, "count": 277 }, "SmallWallJump.Step.mean": { "value": 5539990.0, "min": 19906.0, "max": 5539990.0, "count": 277 }, "SmallWallJump.Step.sum": { "value": 5539990.0, "min": 19906.0, "max": 5539990.0, "count": 277 }, "SmallWallJump.Policy.ExtrinsicValueEstimate.mean": { "value": 0.9011476635932922, "min": -0.4881293773651123, "max": 0.9083206057548523, "count": 277 }, "SmallWallJump.Policy.ExtrinsicValueEstimate.sum": { "value": 1179.602294921875, "min": -156.6895294189453, "max": 1206.5859375, "count": 277 }, "SmallWallJump.Environment.CumulativeReward.mean": { "value": 0.9520741039965334, "min": -1.0653809613504563, "max": 0.9619308807722704, "count": 277 }, "SmallWallJump.Environment.CumulativeReward.sum": { "value": 1246.265002131462, "min": -357.96800301375333, "max": 1280.3300023078918, "count": 277 }, "SmallWallJump.Policy.ExtrinsicReward.mean": { "value": 0.9520741039965334, "min": -1.0653809613504563, "max": 0.9619308807722704, "count": 277 }, "SmallWallJump.Policy.ExtrinsicReward.sum": { "value": 1246.265002131462, "min": -357.96800301375333, "max": 1280.3300023078918, "count": 277 }, "SmallWallJump.Losses.PolicyLoss.mean": { "value": 0.020284520431111255, "min": 0.014728642107608417, "max": 0.027711384867628412, "count": 250 }, "SmallWallJump.Losses.PolicyLoss.sum": { "value": 0.10142260215555628, "min": 0.06312889838591218, "max": 0.13855692433814207, "count": 250 }, "SmallWallJump.Losses.ValueLoss.mean": { "value": 0.014050534221072062, "min": 0.004349971085321158, "max": 0.12879822564621765, "count": 250 }, "SmallWallJump.Losses.ValueLoss.sum": { "value": 0.0702526711053603, "min": 0.0178363644372439, "max": 0.6439911282310883, "count": 250 }, "SmallWallJump.Policy.LearningRate.mean": { "value": 5.532878156039934e-07, "min": 5.532878156039934e-07, "max": 0.00029937621020793, "count": 250 }, "SmallWallJump.Policy.LearningRate.sum": { "value": 2.7664390780199667e-06, "min": 2.7664390780199667e-06, "max": 0.00149128866290378, "count": 250 }, "SmallWallJump.Policy.Epsilon.mean": { "value": 0.100184396, "min": 0.100184396, "max": 0.19979207000000002, "count": 250 }, "SmallWallJump.Policy.Epsilon.sum": { "value": 0.50092198, "min": 0.40878648000000006, "max": 0.9970962200000001, "count": 250 }, "SmallWallJump.Policy.Beta.mean": { "value": 1.9201360399999894e-05, "min": 1.9201360399999894e-05, "max": 0.004989624293, "count": 250 }, "SmallWallJump.Policy.Beta.sum": { "value": 9.600680199999947e-05, "min": 9.600680199999947e-05, "max": 0.024855101378000004, "count": 250 }, "SmallWallJump.IsTraining.mean": { "value": 0.0, "min": 0.0, "max": 1.0, "count": 277 }, "SmallWallJump.IsTraining.sum": { "value": 0.0, "min": 0.0, "max": 1.0, "count": 277 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693677305", "python_version": "3.10.10 (main, Mar 21 2023, 18:45:11) [GCC 11.2.0]", "command_line_arguments": "/home/yaohua/miniconda3/envs/drl2/bin/mlagents-learn config/ppo/WallJump.yaml --run-id=walljump_test_02 --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0.dev20230902+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1693694847" }, "total": 17542.104710366002, "count": 1, "self": 0.0042794360051630065, "children": { "run_training.setup": { "total": 0.2931904069992015, "count": 1, "self": 0.2931904069992015 }, "TrainerController.start_learning": { "total": 17541.807240522998, "count": 1, "self": 23.918419953661214, "children": { "TrainerController._reset_env": { "total": 4.204136708998703, "count": 1, "self": 4.204136708998703 }, "TrainerController.advance": { "total": 17513.588606540332, "count": 1649473, "self": 25.197562763569294, "children": { "env_step": { "total": 12823.833156169661, "count": 1649473, "self": 9685.534935636744, "children": { "SubprocessEnvManager._take_step": { "total": 3124.260964101806, "count": 1649473, "self": 82.05208733542531, "children": { "TorchPolicy.evaluate": { "total": 3042.208876766381, "count": 2084685, "self": 3042.208876766381 } } }, "workers": { "total": 14.037256431111018, "count": 1649473, "self": 0.0, "children": { "worker_root": { "total": 17510.696612694024, "count": 1649473, "is_parallel": true, "self": 9345.517714997717, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019906219968106598, "count": 2, "is_parallel": true, "self": 0.00035755999124376103, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016330620055668987, "count": 12, "is_parallel": true, "self": 0.0016330620055668987 } } }, "UnityEnvironment.step": { "total": 0.015547777999017853, "count": 1, "is_parallel": true, "self": 0.00021877400286030024, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022080600319895893, "count": 1, "is_parallel": true, "self": 0.00022080600319895893 }, "communicator.exchange": { "total": 0.014489156994386576, "count": 1, "is_parallel": true, "self": 0.014489156994386576 }, "steps_from_proto": { "total": 0.000619040998572018, "count": 2, "is_parallel": true, "self": 0.00011063999409088865, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005084010044811293, "count": 12, "is_parallel": true, "self": 0.0005084010044811293 } } } } } } }, "UnityEnvironment.step": { "total": 8165.178897696307, "count": 1649472, "is_parallel": true, "self": 376.3883987422014, "children": { "UnityEnvironment._generate_step_input": { "total": 164.2484304461541, "count": 1649472, "is_parallel": true, "self": 164.2484304461541 }, "communicator.exchange": { "total": 6517.66026597649, "count": 1649472, "is_parallel": true, "self": 6517.66026597649 }, "steps_from_proto": { "total": 1106.8818025314613, "count": 3298944, "is_parallel": true, "self": 223.7129027638657, "children": { "_process_rank_one_or_two_observation": { "total": 883.1688997675956, "count": 19793664, "is_parallel": true, "self": 883.1688997675956 } } } } } } } } } } }, "trainer_advance": { "total": 4664.557887607101, "count": 3298946, "self": 64.85026829431445, "children": { "process_trajectory": { "total": 1843.857758643273, "count": 3298946, "self": 1841.3516648222503, "children": { "RLTrainer._checkpoint": { "total": 2.5060938210226595, "count": 51, "self": 2.5060938210226595 } } }, "_update_policy": { "total": 2755.849860669514, "count": 6056, "self": 2171.7557627543065, "children": { "TorchPPOOptimizer.update": { "total": 584.0940979152074, "count": 72672, "self": 584.0940979152074 } } } } } } }, "trainer_threads": { "total": 5.440015229396522e-07, "count": 1, "self": 5.440015229396522e-07 }, "TrainerController._save_models": { "total": 0.09607677600433817, "count": 1, "self": 0.0014533749999827705, "children": { "RLTrainer._checkpoint": { "total": 0.0946234010043554, "count": 2, "self": 0.0946234010043554 } } } } } } }