{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7170038819313049, "min": 0.7170038819313049, "max": 2.849374532699585, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6814.40478515625, "min": 6814.40478515625, "max": 29086.416015625, "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": 12.871124267578125, "min": 0.31479066610336304, "max": 12.871124267578125, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2509.869140625, "min": 61.06938934326172, "max": 2610.96142578125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07426913766177641, "min": 0.062340034129567144, "max": 0.07728020640694441, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29707655064710564, "min": 0.24936013651826858, "max": 0.38640103203472204, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19394765940367006, "min": 0.12874440204434318, "max": 0.2811643300103206, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7757906376146803, "min": 0.5149776081773727, "max": 1.3864895006020863, "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": 25.454545454545453, "min": 3.5454545454545454, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 156.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.5454545454545454, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 156.0, "max": 1392.0, "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": "1783022791", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics --force", "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": "1783023580" }, "total": 789.139154603, "count": 1, "self": 0.9505620250001812, "children": { "run_training.setup": { "total": 0.03804915199998504, "count": 1, "self": 0.03804915199998504 }, "TrainerController.start_learning": { "total": 788.1505434259998, "count": 1, "self": 0.5642361140489811, "children": { "TrainerController._reset_env": { "total": 3.984056598999814, "count": 1, "self": 3.984056598999814 }, "TrainerController.advance": { "total": 783.3918465949519, "count": 18192, "self": 0.5569624301406293, "children": { "env_step": { "total": 593.9856056248818, "count": 18192, "self": 488.390564265801, "children": { "SubprocessEnvManager._take_step": { "total": 105.25798858102007, "count": 18192, "self": 1.8763829380568495, "children": { "TorchPolicy.evaluate": { "total": 103.38160564296322, "count": 18192, "self": 103.38160564296322 } } }, "workers": { "total": 0.33705277806075173, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 780.7887304509841, "count": 18192, "is_parallel": true, "self": 352.06102459597514, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004853637000451272, "count": 1, "is_parallel": true, "self": 0.0007601290008096839, "children": { "_process_rank_one_or_two_observation": { "total": 0.004093507999641588, "count": 10, "is_parallel": true, "self": 0.004093507999641588 } } }, "UnityEnvironment.step": { "total": 0.09955226599959133, "count": 1, "is_parallel": true, "self": 0.0006345179999698303, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0023351079998974456, "count": 1, "is_parallel": true, "self": 0.0023351079998974456 }, "communicator.exchange": { "total": 0.08962097899984656, "count": 1, "is_parallel": true, "self": 0.08962097899984656 }, "steps_from_proto": { "total": 0.006961660999877495, "count": 1, "is_parallel": true, "self": 0.0003846850022455328, "children": { "_process_rank_one_or_two_observation": { "total": 0.006576975997631962, "count": 10, "is_parallel": true, "self": 0.006576975997631962 } } } } } } }, "UnityEnvironment.step": { "total": 428.72770585500894, "count": 18191, "is_parallel": true, "self": 12.516839495273416, "children": { "UnityEnvironment._generate_step_input": { "total": 5.7071867639260745, "count": 18191, "is_parallel": true, "self": 5.7071867639260745 }, "communicator.exchange": { "total": 340.036357533967, "count": 18191, "is_parallel": true, "self": 340.036357533967 }, "steps_from_proto": { "total": 70.46732206184242, "count": 18191, "is_parallel": true, "self": 12.606582177909331, "children": { "_process_rank_one_or_two_observation": { "total": 57.86073988393309, "count": 181910, "is_parallel": true, "self": 57.86073988393309 } } } } } } } } } } }, "trainer_advance": { "total": 188.8492785399294, "count": 18192, "self": 0.7245181098915054, "children": { "process_trajectory": { "total": 38.977636828044524, "count": 18192, "self": 38.19412665204436, "children": { "RLTrainer._checkpoint": { "total": 0.7835101760001635, "count": 4, "self": 0.7835101760001635 } } }, "_update_policy": { "total": 149.14712360199337, "count": 90, "self": 71.63568960995963, "children": { "TorchPPOOptimizer.update": { "total": 77.51143399203374, "count": 4587, "self": 77.51143399203374 } } } } } } }, "trainer_threads": { "total": 1.27099974633893e-06, "count": 1, "self": 1.27099974633893e-06 }, "TrainerController._save_models": { "total": 0.21040284699938638, "count": 1, "self": 0.0009470219993090723, "children": { "RLTrainer._checkpoint": { "total": 0.2094558250000773, "count": 1, "self": 0.2094558250000773 } } } } } } }