{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9684996008872986, "min": 0.9684996008872986, "max": 2.877516031265259, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9268.541015625, "min": 9268.541015625, "max": 29500.294921875, "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": 12.814105033874512, "min": 0.3878885507583618, "max": 12.814105033874512, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2498.75048828125, "min": 75.25038146972656, "max": 2596.07373046875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07260980931716723, "min": 0.06082252065193733, "max": 0.07464818893680715, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29043923726866894, "min": 0.24329008260774931, "max": 0.37324094468403574, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2134869284927845, "min": 0.13613263558135277, "max": 0.27794229247990776, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.853947713971138, "min": 0.5445305423254111, "max": 1.3897114623995388, "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.Environment.CumulativeReward.mean": { "value": 25.431818181818183, "min": 3.2954545454545454, "max": 25.431818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 145.0, "max": 1367.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.2954545454545454, "max": 25.431818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 145.0, "max": 1367.0, "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": "1718046838", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718047486" }, "total": 647.8044477630001, "count": 1, "self": 0.7625262090000433, "children": { "run_training.setup": { "total": 0.07379764400002387, "count": 1, "self": 0.07379764400002387 }, "TrainerController.start_learning": { "total": 646.96812391, "count": 1, "self": 0.9626521629625131, "children": { "TrainerController._reset_env": { "total": 3.8636808199998995, "count": 1, "self": 3.8636808199998995 }, "TrainerController.advance": { "total": 642.0322991120374, "count": 18204, "self": 0.5015276620306395, "children": { "env_step": { "total": 641.5307714500068, "count": 18204, "self": 497.5059983040219, "children": { "SubprocessEnvManager._take_step": { "total": 143.55134418099396, "count": 18204, "self": 2.8236436499846604, "children": { "TorchPolicy.evaluate": { "total": 140.7277005310093, "count": 18204, "self": 140.7277005310093 } } }, "workers": { "total": 0.4734289649909442, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 644.7046288020165, "count": 18204, "is_parallel": true, "self": 301.87143989301285, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005259889000171825, "count": 1, "is_parallel": true, "self": 0.0014425670005948632, "children": { "_process_rank_one_or_two_observation": { "total": 0.0038173219995769614, "count": 10, "is_parallel": true, "self": 0.0038173219995769614 } } }, "UnityEnvironment.step": { "total": 0.11107322499992733, "count": 1, "is_parallel": true, "self": 0.0009599619993423403, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005370420003600884, "count": 1, "is_parallel": true, "self": 0.0005370420003600884 }, "communicator.exchange": { "total": 0.10678837200021007, "count": 1, "is_parallel": true, "self": 0.10678837200021007 }, "steps_from_proto": { "total": 0.0027878490000148304, "count": 1, "is_parallel": true, "self": 0.0005153979996066482, "children": { "_process_rank_one_or_two_observation": { "total": 0.002272451000408182, "count": 10, "is_parallel": true, "self": 0.002272451000408182 } } } } } } }, "UnityEnvironment.step": { "total": 342.83318890900364, "count": 18203, "is_parallel": true, "self": 16.66626401300482, "children": { "UnityEnvironment._generate_step_input": { "total": 8.386571640010516, "count": 18203, "is_parallel": true, "self": 8.386571640010516 }, "communicator.exchange": { "total": 270.7125183689982, "count": 18203, "is_parallel": true, "self": 270.7125183689982 }, "steps_from_proto": { "total": 47.06783488699011, "count": 18203, "is_parallel": true, "self": 9.537771814955704, "children": { "_process_rank_one_or_two_observation": { "total": 37.53006307203441, "count": 182030, "is_parallel": true, "self": 37.53006307203441 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019714600011866423, "count": 1, "self": 0.00019714600011866423, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 634.5335178327819, "count": 852663, "is_parallel": true, "self": 19.741521149714572, "children": { "process_trajectory": { "total": 347.25833056406645, "count": 852663, "is_parallel": true, "self": 346.48614652006563, "children": { "RLTrainer._checkpoint": { "total": 0.7721840440008236, "count": 4, "is_parallel": true, "self": 0.7721840440008236 } } }, "_update_policy": { "total": 267.5336661190008, "count": 90, "is_parallel": true, "self": 79.16197539199038, "children": { "TorchPPOOptimizer.update": { "total": 188.37169072701045, "count": 4584, "is_parallel": true, "self": 188.37169072701045 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10929466900006446, "count": 1, "self": 0.0016495080003551266, "children": { "RLTrainer._checkpoint": { "total": 0.10764516099970933, "count": 1, "self": 0.10764516099970933 } } } } } } }