{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.2491800785064697, "min": 1.222576379776001, "max": 2.8629627227783203, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11968.39453125, "min": 11968.39453125, "max": 29445.572265625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.353843688964844, "min": 0.4741840958595276, "max": 12.353843688964844, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2408.99951171875, "min": 91.99171447753906, "max": 2498.68359375, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.mean": { "value": 3.674806833267212, "min": 0.9938725233078003, "max": 6.073102951049805, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.sum": { "value": 716.5873413085938, "min": 192.81126403808594, "max": 1244.986083984375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06777194152870353, "min": 0.06302924508117048, "max": 0.07236553499715942, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2710877661148141, "min": 0.2552396428749061, "max": 0.3443801682134269, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.10351137743861068, "min": 0.10351137743861068, "max": 0.18740646307374917, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.4140455097544427, "min": 0.4140455097544427, "max": 0.9094571824751648, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Losses.CuriosityForwardLoss.mean": { "value": 0.035778052401820234, "min": 0.03542665550667866, "max": 0.1282479904692474, "count": 20 }, "SnowballTarget.Losses.CuriosityForwardLoss.sum": { "value": 0.14311220960728094, "min": 0.14311220960728094, "max": 0.5129919618769896, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.mean": { "value": 1.116723170175272, "min": 1.0920064367500006, "max": 2.7914933008598344, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.sum": { "value": 4.466892680701088, "min": 4.466892680701088, "max": 12.919521261663997, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.431818181818183, "min": 3.4545454545454546, "max": 24.431818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1075.0, "min": 152.0, "max": 1332.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.431818181818183, "min": 3.4545454545454546, "max": 24.431818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1075.0, "min": 152.0, "max": 1332.0, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.mean": { "value": 7.333064267581159, "min": 7.219717323373665, "max": 14.633068123730746, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.sum": { "value": 322.654827773571, "min": 322.654827773571, "max": 804.818746805191, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679160626", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1679161133" }, "total": 507.111704271, "count": 1, "self": 0.43222254099998736, "children": { "run_training.setup": { "total": 0.1865317499999719, "count": 1, "self": 0.1865317499999719 }, "TrainerController.start_learning": { "total": 506.49294998000005, "count": 1, "self": 0.5081599140000321, "children": { "TrainerController._reset_env": { "total": 8.837328146000004, "count": 1, "self": 8.837328146000004 }, "TrainerController.advance": { "total": 497.01134754900005, "count": 18205, "self": 0.2616570100057629, "children": { "env_step": { "total": 496.7496905389943, "count": 18205, "self": 380.87428996799554, "children": { "SubprocessEnvManager._take_step": { "total": 115.62187331799737, "count": 18205, "self": 1.6712460750011928, "children": { "TorchPolicy.evaluate": { "total": 113.95062724299618, "count": 18205, "self": 113.95062724299618 } } }, "workers": { "total": 0.2535272530013799, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 505.04418955801, "count": 18205, "is_parallel": true, "self": 273.8308054529998, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006003792999990765, "count": 1, "is_parallel": true, "self": 0.004280852000078994, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017229409999117706, "count": 10, "is_parallel": true, "self": 0.0017229409999117706 } } }, "UnityEnvironment.step": { "total": 0.03795868100002053, "count": 1, "is_parallel": true, "self": 0.0005486439999913273, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038920999998026673, "count": 1, "is_parallel": true, "self": 0.00038920999998026673 }, "communicator.exchange": { "total": 0.03521615100004283, "count": 1, "is_parallel": true, "self": 0.03521615100004283 }, "steps_from_proto": { "total": 0.0018046760000061113, "count": 1, "is_parallel": true, "self": 0.00036261800005377154, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014420579999523397, "count": 10, "is_parallel": true, "self": 0.0014420579999523397 } } } } } } }, "UnityEnvironment.step": { "total": 231.21338410501016, "count": 18204, "is_parallel": true, "self": 9.416791271996885, "children": { "UnityEnvironment._generate_step_input": { "total": 5.030509783006551, "count": 18204, "is_parallel": true, "self": 5.030509783006551 }, "communicator.exchange": { "total": 186.38878381800572, "count": 18204, "is_parallel": true, "self": 186.38878381800572 }, "steps_from_proto": { "total": 30.377299232001008, "count": 18204, "is_parallel": true, "self": 5.970715027996619, "children": { "_process_rank_one_or_two_observation": { "total": 24.40658420400439, "count": 182040, "is_parallel": true, "self": 24.40658420400439 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010696599997572775, "count": 1, "self": 0.00010696599997572775, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 494.13016796800787, "count": 353468, "is_parallel": true, "self": 8.546416368007783, "children": { "process_trajectory": { "total": 255.68446498999953, "count": 353468, "is_parallel": true, "self": 254.47745920499966, "children": { "RLTrainer._checkpoint": { "total": 1.2070057849998648, "count": 4, "is_parallel": true, "self": 1.2070057849998648 } } }, "_update_policy": { "total": 229.89928661000056, "count": 90, "is_parallel": true, "self": 141.5640260899999, "children": { "TorchPPOOptimizer.update": { "total": 88.33526052000065, "count": 4584, "is_parallel": true, "self": 88.33526052000065 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13600740499998665, "count": 1, "self": 0.0008929389999821069, "children": { "RLTrainer._checkpoint": { "total": 0.13511446600000454, "count": 1, "self": 0.13511446600000454 } } } } } } }