{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8400298953056335, "min": 0.8400298953056335, "max": 2.8678245544433594, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7983.64404296875, "min": 7983.64404296875, "max": 29274.75390625, "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": 12.966197967529297, "min": 0.2994891405105591, "max": 12.966197967529297, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2528.40869140625, "min": 58.100894927978516, "max": 2644.861083984375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07070839912850323, "min": 0.06189187683219857, "max": 0.0750947887879139, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2828335965140129, "min": 0.2475675073287943, "max": 0.3754739439395695, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20452913400881428, "min": 0.1114377919253528, "max": 0.2819243719180425, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8181165360352571, "min": 0.4457511677014112, "max": 1.3946680593139984, "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.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.Environment.CumulativeReward.mean": { "value": 25.295454545454547, "min": 3.340909090909091, "max": 25.613636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1113.0, "min": 147.0, "max": 1401.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.295454545454547, "min": 3.340909090909091, "max": 25.613636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1113.0, "min": 147.0, "max": 1401.0, "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": "1760236227", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/environment/miniconda3/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1760236663" }, "total": 436.0496181699999, "count": 1, "self": 0.3724983700000166, "children": { "run_training.setup": { "total": 0.03950861599992095, "count": 1, "self": 0.03950861599992095 }, "TrainerController.start_learning": { "total": 435.637611184, "count": 1, "self": 0.24247217100344187, "children": { "TrainerController._reset_env": { "total": 5.043811949000087, "count": 1, "self": 5.043811949000087 }, "TrainerController.advance": { "total": 430.2857025269964, "count": 18192, "self": 0.2453694860203086, "children": { "env_step": { "total": 309.33766430598644, "count": 18192, "self": 249.66192985999032, "children": { "SubprocessEnvManager._take_step": { "total": 59.52099100599423, "count": 18192, "self": 0.9609338259965625, "children": { "TorchPolicy.evaluate": { "total": 58.56005717999767, "count": 18192, "self": 58.56005717999767 } } }, "workers": { "total": 0.15474344000188012, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 434.56690710098394, "count": 18192, "is_parallel": true, "self": 212.2948464819774, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00404552399993463, "count": 1, "is_parallel": true, "self": 0.000952261000065846, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030932629998687844, "count": 10, "is_parallel": true, "self": 0.0030932629998687844 } } }, "UnityEnvironment.step": { "total": 0.037681925999891064, "count": 1, "is_parallel": true, "self": 0.0005555289999392699, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005845460000273306, "count": 1, "is_parallel": true, "self": 0.0005845460000273306 }, "communicator.exchange": { "total": 0.03500822599994535, "count": 1, "is_parallel": true, "self": 0.03500822599994535 }, "steps_from_proto": { "total": 0.0015336249999791107, "count": 1, "is_parallel": true, "self": 0.000289654999846789, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012439700001323217, "count": 10, "is_parallel": true, "self": 0.0012439700001323217 } } } } } } }, "UnityEnvironment.step": { "total": 222.27206061900654, "count": 18191, "is_parallel": true, "self": 9.005520135014649, "children": { "UnityEnvironment._generate_step_input": { "total": 4.583799466007008, "count": 18191, "is_parallel": true, "self": 4.583799466007008 }, "communicator.exchange": { "total": 183.67476146198646, "count": 18191, "is_parallel": true, "self": 183.67476146198646 }, "steps_from_proto": { "total": 25.007979555998418, "count": 18191, "is_parallel": true, "self": 4.7849640299457405, "children": { "_process_rank_one_or_two_observation": { "total": 20.223015526052677, "count": 181910, "is_parallel": true, "self": 20.223015526052677 } } } } } } } } } } }, "trainer_advance": { "total": 120.70266873498963, "count": 18192, "self": 0.29831738898644744, "children": { "process_trajectory": { "total": 23.6536174510029, "count": 18192, "self": 23.33694818200263, "children": { "RLTrainer._checkpoint": { "total": 0.3166692690002719, "count": 4, "self": 0.3166692690002719 } } }, "_update_policy": { "total": 96.75073389500028, "count": 90, "self": 28.356185667010095, "children": { "TorchPPOOptimizer.update": { "total": 68.39454822799019, "count": 4587, "self": 68.39454822799019 } } } } } } }, "trainer_threads": { "total": 1.077000206350931e-06, "count": 1, "self": 1.077000206350931e-06 }, "TrainerController._save_models": { "total": 0.06562345999986974, "count": 1, "self": 0.0008230509997702029, "children": { "RLTrainer._checkpoint": { "total": 0.06480040900009953, "count": 1, "self": 0.06480040900009953 } } } } } } }