{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8117265701293945, "min": 0.8117265701293945, "max": 2.850313186645508, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7714.6494140625, "min": 7714.6494140625, "max": 29095.99609375, "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": 13.212973594665527, "min": 0.2903619706630707, "max": 13.212973594665527, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2576.52978515625, "min": 56.330223083496094, "max": 2682.618408203125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07103065175004875, "min": 0.06222772718668007, "max": 0.07103065175004875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.284122607000195, "min": 0.2598804983175725, "max": 0.3529311007040115, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18548467244003333, "min": 0.125716559273903, "max": 0.30810030418283796, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7419386897601333, "min": 0.502866237095612, "max": 1.442118267218272, "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": 26.068181818181817, "min": 3.6363636363636362, "max": 26.072727272727274, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1147.0, "min": 160.0, "max": 1434.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.068181818181817, "min": 3.6363636363636362, "max": 26.072727272727274, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1147.0, "min": 160.0, "max": 1434.0, "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": "1750260002", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750260431" }, "total": 428.8306856230001, "count": 1, "self": 0.44109498900007793, "children": { "run_training.setup": { "total": 0.022679197000002205, "count": 1, "self": 0.022679197000002205 }, "TrainerController.start_learning": { "total": 428.366911437, "count": 1, "self": 0.3596310660024642, "children": { "TrainerController._reset_env": { "total": 3.000086556000042, "count": 1, "self": 3.000086556000042 }, "TrainerController.advance": { "total": 424.92275489899754, "count": 18192, "self": 0.3744548689882663, "children": { "env_step": { "total": 306.5134472239978, "count": 18192, "self": 235.807603178002, "children": { "SubprocessEnvManager._take_step": { "total": 70.48312358099923, "count": 18192, "self": 1.287579302007373, "children": { "TorchPolicy.evaluate": { "total": 69.19554427899186, "count": 18192, "self": 69.19554427899186 } } }, "workers": { "total": 0.22272046499654152, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 426.9758367229927, "count": 18192, "is_parallel": true, "self": 220.17347120099004, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0049593599999866456, "count": 1, "is_parallel": true, "self": 0.0034443469999700937, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015150130000165518, "count": 10, "is_parallel": true, "self": 0.0015150130000165518 } } }, "UnityEnvironment.step": { "total": 0.035749159000033615, "count": 1, "is_parallel": true, "self": 0.0006050570000297739, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041545199997017335, "count": 1, "is_parallel": true, "self": 0.00041545199997017335 }, "communicator.exchange": { "total": 0.03265186800001629, "count": 1, "is_parallel": true, "self": 0.03265186800001629 }, "steps_from_proto": { "total": 0.0020767820000173742, "count": 1, "is_parallel": true, "self": 0.0003716690000601375, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017051129999572368, "count": 10, "is_parallel": true, "self": 0.0017051129999572368 } } } } } } }, "UnityEnvironment.step": { "total": 206.80236552200267, "count": 18191, "is_parallel": true, "self": 9.910385878999534, "children": { "UnityEnvironment._generate_step_input": { "total": 5.485092280005233, "count": 18191, "is_parallel": true, "self": 5.485092280005233 }, "communicator.exchange": { "total": 158.79238652700548, "count": 18191, "is_parallel": true, "self": 158.79238652700548 }, "steps_from_proto": { "total": 32.61450083599243, "count": 18191, "is_parallel": true, "self": 5.8078442800061225, "children": { "_process_rank_one_or_two_observation": { "total": 26.806656555986308, "count": 181910, "is_parallel": true, "self": 26.806656555986308 } } } } } } } } } } }, "trainer_advance": { "total": 118.03485280601149, "count": 18192, "self": 0.4423282950111229, "children": { "process_trajectory": { "total": 26.43572540800062, "count": 18192, "self": 25.997884323000562, "children": { "RLTrainer._checkpoint": { "total": 0.43784108500005914, "count": 4, "self": 0.43784108500005914 } } }, "_update_policy": { "total": 91.15679910299974, "count": 90, "self": 37.5986370930043, "children": { "TorchPPOOptimizer.update": { "total": 53.55816200999544, "count": 4587, "self": 53.55816200999544 } } } } } } }, "trainer_threads": { "total": 8.399999842367833e-07, "count": 1, "self": 8.399999842367833e-07 }, "TrainerController._save_models": { "total": 0.08443807599996944, "count": 1, "self": 0.0009082180000632434, "children": { "RLTrainer._checkpoint": { "total": 0.0835298579999062, "count": 1, "self": 0.0835298579999062 } } } } } } }