{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9284960031509399, "min": 0.9284960031509399, "max": 2.866152286529541, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8824.42578125, "min": 8824.42578125, "max": 29257.681640625, "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": 13.097471237182617, "min": 0.18841716647148132, "max": 13.097471237182617, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2554.0068359375, "min": 36.55292892456055, "max": 2654.40283203125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07075534365453766, "min": 0.06311876177913327, "max": 0.07416931517375404, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28302137461815063, "min": 0.25247504711653307, "max": 0.3652134789587637, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20408615692719526, "min": 0.11328667096163639, "max": 0.3025279199229736, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.816344627708781, "min": 0.45314668384654555, "max": 1.4447184339457868, "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": 26.09090909090909, "min": 3.159090909090909, "max": 26.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1148.0, "min": 139.0, "max": 1422.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.09090909090909, "min": 3.159090909090909, "max": 26.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1148.0, "min": 139.0, "max": 1422.0, "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": "1739269668", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739270081" }, "total": 412.986179819, "count": 1, "self": 0.44139238999991903, "children": { "run_training.setup": { "total": 0.024023426999974618, "count": 1, "self": 0.024023426999974618 }, "TrainerController.start_learning": { "total": 412.5207640020001, "count": 1, "self": 0.3019091959697562, "children": { "TrainerController._reset_env": { "total": 3.522105096999894, "count": 1, "self": 3.522105096999894 }, "TrainerController.advance": { "total": 408.6110043610306, "count": 18192, "self": 0.34584552101432564, "children": { "env_step": { "total": 287.08830194903317, "count": 18192, "self": 218.47415363400023, "children": { "SubprocessEnvManager._take_step": { "total": 68.42678944698378, "count": 18192, "self": 1.1948726379912387, "children": { "TorchPolicy.evaluate": { "total": 67.23191680899254, "count": 18192, "self": 67.23191680899254 } } }, "workers": { "total": 0.18735886804915935, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 411.010822681988, "count": 18192, "is_parallel": true, "self": 219.38780775800933, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005318173999967257, "count": 1, "is_parallel": true, "self": 0.0037966080001297087, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015215659998375486, "count": 10, "is_parallel": true, "self": 0.0015215659998375486 } } }, "UnityEnvironment.step": { "total": 0.058729175000053147, "count": 1, "is_parallel": true, "self": 0.0005813730001591466, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037887600001340616, "count": 1, "is_parallel": true, "self": 0.00037887600001340616 }, "communicator.exchange": { "total": 0.0559685629998512, "count": 1, "is_parallel": true, "self": 0.0559685629998512 }, "steps_from_proto": { "total": 0.0018003630000293924, "count": 1, "is_parallel": true, "self": 0.0003799070000241045, "children": { "_process_rank_one_or_two_observation": { "total": 0.001420456000005288, "count": 10, "is_parallel": true, "self": 0.001420456000005288 } } } } } } }, "UnityEnvironment.step": { "total": 191.62301492397864, "count": 18191, "is_parallel": true, "self": 9.481189966960073, "children": { "UnityEnvironment._generate_step_input": { "total": 5.314903814012496, "count": 18191, "is_parallel": true, "self": 5.314903814012496 }, "communicator.exchange": { "total": 146.80906143398602, "count": 18191, "is_parallel": true, "self": 146.80906143398602 }, "steps_from_proto": { "total": 30.01785970902006, "count": 18191, "is_parallel": true, "self": 5.19137117092464, "children": { "_process_rank_one_or_two_observation": { "total": 24.82648853809542, "count": 181910, "is_parallel": true, "self": 24.82648853809542 } } } } } } } } } } }, "trainer_advance": { "total": 121.17685689098312, "count": 18192, "self": 0.3663920200103803, "children": { "process_trajectory": { "total": 26.248867436971977, "count": 18192, "self": 25.715260669972395, "children": { "RLTrainer._checkpoint": { "total": 0.5336067669995828, "count": 4, "self": 0.5336067669995828 } } }, "_update_policy": { "total": 94.56159743400076, "count": 90, "self": 37.97110824801007, "children": { "TorchPPOOptimizer.update": { "total": 56.59048918599069, "count": 4587, "self": 56.59048918599069 } } } } } } }, "trainer_threads": { "total": 8.590000106778461e-07, "count": 1, "self": 8.590000106778461e-07 }, "TrainerController._save_models": { "total": 0.0857444889998078, "count": 1, "self": 0.0008655679998810228, "children": { "RLTrainer._checkpoint": { "total": 0.08487892099992678, "count": 1, "self": 0.08487892099992678 } } } } } } }