{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9818022847175598, "min": 0.9818022847175598, "max": 2.8596558570861816, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9331.048828125, "min": 9331.048828125, "max": 29191.3671875, "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": 12.862401962280273, "min": 0.3554244637489319, "max": 12.862401962280273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2508.16845703125, "min": 68.95234680175781, "max": 2616.968505859375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07597849061016412, "min": 0.062196647276127184, "max": 0.07967054171775304, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3039139624406565, "min": 0.26265283332745015, "max": 0.37630058490464635, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17313816420295658, "min": 0.13385328174313055, "max": 0.2801930135955998, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6925526568118263, "min": 0.5354131269725222, "max": 1.3726457509340027, "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": 25.022727272727273, "min": 3.8181818181818183, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1101.0, "min": 168.0, "max": 1406.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.022727272727273, "min": 3.8181818181818183, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1101.0, "min": 168.0, "max": 1406.0, "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": "1754779011", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1754779441" }, "total": 430.24518860800003, "count": 1, "self": 0.7424776360003307, "children": { "run_training.setup": { "total": 0.02275969599986638, "count": 1, "self": 0.02275969599986638 }, "TrainerController.start_learning": { "total": 429.47995127599984, "count": 1, "self": 0.3555414460031443, "children": { "TrainerController._reset_env": { "total": 3.238929581000093, "count": 1, "self": 3.238929581000093 }, "TrainerController.advance": { "total": 425.76174181599663, "count": 18192, "self": 0.3792440510076176, "children": { "env_step": { "total": 306.48708975498903, "count": 18192, "self": 235.69907829200133, "children": { "SubprocessEnvManager._take_step": { "total": 70.56701062500679, "count": 18192, "self": 1.2410581010094575, "children": { "TorchPolicy.evaluate": { "total": 69.32595252399733, "count": 18192, "self": 69.32595252399733 } } }, "workers": { "total": 0.22100083798090964, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 427.9140334210165, "count": 18192, "is_parallel": true, "self": 221.21649606701067, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0058687709999958315, "count": 1, "is_parallel": true, "self": 0.004349276999619178, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015194940003766533, "count": 10, "is_parallel": true, "self": 0.0015194940003766533 } } }, "UnityEnvironment.step": { "total": 0.0350942140000825, "count": 1, "is_parallel": true, "self": 0.0006042260004051059, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037959899987072276, "count": 1, "is_parallel": true, "self": 0.00037959899987072276 }, "communicator.exchange": { "total": 0.032164711999939755, "count": 1, "is_parallel": true, "self": 0.032164711999939755 }, "steps_from_proto": { "total": 0.0019456769998669188, "count": 1, "is_parallel": true, "self": 0.0004113919999326754, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015342849999342434, "count": 10, "is_parallel": true, "self": 0.0015342849999342434 } } } } } } }, "UnityEnvironment.step": { "total": 206.69753735400582, "count": 18191, "is_parallel": true, "self": 9.974921551029183, "children": { "UnityEnvironment._generate_step_input": { "total": 5.555946872000504, "count": 18191, "is_parallel": true, "self": 5.555946872000504 }, "communicator.exchange": { "total": 158.8176559279966, "count": 18191, "is_parallel": true, "self": 158.8176559279966 }, "steps_from_proto": { "total": 32.34901300297952, "count": 18191, "is_parallel": true, "self": 5.717800069946634, "children": { "_process_rank_one_or_two_observation": { "total": 26.631212933032884, "count": 181910, "is_parallel": true, "self": 26.631212933032884 } } } } } } } } } } }, "trainer_advance": { "total": 118.89540800999998, "count": 18192, "self": 0.43770896699425066, "children": { "process_trajectory": { "total": 27.59682141600456, "count": 18192, "self": 27.16541614900484, "children": { "RLTrainer._checkpoint": { "total": 0.43140526699971815, "count": 4, "self": 0.43140526699971815 } } }, "_update_policy": { "total": 90.86087762700117, "count": 90, "self": 37.16316140200297, "children": { "TorchPPOOptimizer.update": { "total": 53.6977162249982, "count": 4587, "self": 53.6977162249982 } } } } } } }, "trainer_threads": { "total": 1.9269998574600322e-06, "count": 1, "self": 1.9269998574600322e-06 }, "TrainerController._save_models": { "total": 0.12373650600011388, "count": 1, "self": 0.0010927200000878656, "children": { "RLTrainer._checkpoint": { "total": 0.12264378600002601, "count": 1, "self": 0.12264378600002601 } } } } } } }