{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0177090167999268, "min": 0.9997448921203613, "max": 2.874314785003662, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9750.669921875, "min": 9750.669921875, "max": 29530.7109375, "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": 13.024076461791992, "min": 0.48631271719932556, "max": 13.024076461791992, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2539.69482421875, "min": 94.34466552734375, "max": 2644.46728515625, "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.Losses.PolicyLoss.mean": { "value": 0.0701133475773246, "min": 0.06234063538902453, "max": 0.07417824209323062, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2804533903092984, "min": 0.24936254155609813, "max": 0.365320383173336, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20536181907735618, "min": 0.12281260192257298, "max": 0.2956460791767812, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8214472763094247, "min": 0.49125040769029193, "max": 1.4227274697200927, "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.CumulativeReward.mean": { "value": 25.454545454545453, "min": 3.5, "max": 26.022727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 154.0, "max": 1404.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.5, "max": 26.022727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 154.0, "max": 1404.0, "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": "1785082279", "python_version": "3.10.6 (main, Oct 24 2022, 16:07:47) [GCC 11.2.0]", "command_line_arguments": "/usr/local/miniconda/envs/mlagents_env/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1785082956" }, "total": 677.6149091380003, "count": 1, "self": 0.581462940000165, "children": { "run_training.setup": { "total": 0.017605408000008538, "count": 1, "self": 0.017605408000008538 }, "TrainerController.start_learning": { "total": 677.0158407900001, "count": 1, "self": 0.9387335810595232, "children": { "TrainerController._reset_env": { "total": 1.9673135620000721, "count": 1, "self": 1.9673135620000721 }, "TrainerController.advance": { "total": 673.9474518309407, "count": 18204, "self": 0.44325892796109656, "children": { "env_step": { "total": 673.5041929029796, "count": 18204, "self": 543.1434112409681, "children": { "SubprocessEnvManager._take_step": { "total": 129.89340406199562, "count": 18204, "self": 2.91605393700911, "children": { "TorchPolicy.evaluate": { "total": 126.97735012498651, "count": 18204, "self": 126.97735012498651 } } }, "workers": { "total": 0.4673776000158796, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 672.9591292479838, "count": 18204, "is_parallel": true, "self": 271.8817506059902, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0033576450000509794, "count": 1, "is_parallel": true, "self": 0.0008194230001663527, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025382219998846267, "count": 10, "is_parallel": true, "self": 0.0025382219998846267 } } }, "UnityEnvironment.step": { "total": 0.08725445000004584, "count": 1, "is_parallel": true, "self": 0.0007908780000889237, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004430339999998978, "count": 1, "is_parallel": true, "self": 0.0004430339999998978 }, "communicator.exchange": { "total": 0.08117980699989857, "count": 1, "is_parallel": true, "self": 0.08117980699989857 }, "steps_from_proto": { "total": 0.00484073100005844, "count": 1, "is_parallel": true, "self": 0.002903558000070916, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019371729999875242, "count": 10, "is_parallel": true, "self": 0.0019371729999875242 } } } } } } }, "UnityEnvironment.step": { "total": 401.0773786419936, "count": 18203, "is_parallel": true, "self": 17.346017173038263, "children": { "UnityEnvironment._generate_step_input": { "total": 8.73557323998034, "count": 18203, "is_parallel": true, "self": 8.73557323998034 }, "communicator.exchange": { "total": 312.1736787999355, "count": 18203, "is_parallel": true, "self": 312.1736787999355 }, "steps_from_proto": { "total": 62.82210942903953, "count": 18203, "is_parallel": true, "self": 11.713906777056991, "children": { "_process_rank_one_or_two_observation": { "total": 51.10820265198254, "count": 182030, "is_parallel": true, "self": 51.10820265198254 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001577240000187885, "count": 1, "self": 0.0001577240000187885, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 669.0715450488644, "count": 530410, "is_parallel": true, "self": 13.845417860803764, "children": { "process_trajectory": { "total": 362.69939353706036, "count": 530410, "is_parallel": true, "self": 361.38851035105995, "children": { "RLTrainer._checkpoint": { "total": 1.3108831860004102, "count": 4, "is_parallel": true, "self": 1.3108831860004102 } } }, "_update_policy": { "total": 292.5267336510003, "count": 90, "is_parallel": true, "self": 80.40367404701715, "children": { "TorchPPOOptimizer.update": { "total": 212.12305960398317, "count": 4584, "is_parallel": true, "self": 212.12305960398317 } } } } } } } } }, "TrainerController._save_models": { "total": 0.16218409199973394, "count": 1, "self": 0.0011168229998474999, "children": { "RLTrainer._checkpoint": { "total": 0.16106726899988644, "count": 1, "self": 0.16106726899988644 } } } } } } }