{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8763975501060486, "min": 0.8763975501060486, "max": 2.8572945594787598, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8367.84375, "min": 8367.84375, "max": 29261.5546875, "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": 2.6689414978027344, "min": 0.2662430703639984, "max": 2.707690954208374, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 520.443603515625, "min": 51.65115737915039, "max": 555.0366821289062, "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": 0.10003961869969155, "min": 0.0905248123767349, "max": 0.107811702386443, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.4001584747987662, "min": 0.3620992495069396, "max": 0.539058511932215, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.12967791397343661, "min": 0.07576893718522518, "max": 0.18305932971070918, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5187116558937465, "min": 0.3030757487409007, "max": 0.9152966485535459, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.104041, "min": 0.104041, "max": 0.24594100000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.416164, "min": 0.416164, "max": 1.19258, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828000000003, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.068181818181817, "min": 4.0227272727272725, "max": 26.704545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1147.0, "min": 177.0, "max": 1445.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.068181818181817, "min": 4.0227272727272725, "max": 26.704545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1147.0, "min": 177.0, "max": 1445.0, "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": "1685810904", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1685811412" }, "total": 507.38135558800013, "count": 1, "self": 0.4349897910001346, "children": { "run_training.setup": { "total": 0.03756740200014974, "count": 1, "self": 0.03756740200014974 }, "TrainerController.start_learning": { "total": 506.90879839499985, "count": 1, "self": 0.6055804119966979, "children": { "TrainerController._reset_env": { "total": 3.5012593080000443, "count": 1, "self": 3.5012593080000443 }, "TrainerController.advance": { "total": 502.6563845340031, "count": 18202, "self": 0.26914107899415285, "children": { "env_step": { "total": 502.38724345500896, "count": 18202, "self": 388.493982257005, "children": { "SubprocessEnvManager._take_step": { "total": 113.6263938040081, "count": 18202, "self": 1.696102391008253, "children": { "TorchPolicy.evaluate": { "total": 111.93029141299985, "count": 18202, "self": 111.93029141299985 } } }, "workers": { "total": 0.2668673939958808, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 505.20555716499484, "count": 18202, "is_parallel": true, "self": 259.1568083640068, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019170760001543385, "count": 1, "is_parallel": true, "self": 0.0005860980002125871, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013309779999417515, "count": 10, "is_parallel": true, "self": 0.0013309779999417515 } } }, "UnityEnvironment.step": { "total": 0.03464088000009724, "count": 1, "is_parallel": true, "self": 0.0005526850000023842, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004172619999280869, "count": 1, "is_parallel": true, "self": 0.0004172619999280869 }, "communicator.exchange": { "total": 0.031639162000146825, "count": 1, "is_parallel": true, "self": 0.031639162000146825 }, "steps_from_proto": { "total": 0.002031771000019944, "count": 1, "is_parallel": true, "self": 0.00039471099967158807, "children": { "_process_rank_one_or_two_observation": { "total": 0.001637060000348356, "count": 10, "is_parallel": true, "self": 0.001637060000348356 } } } } } } }, "UnityEnvironment.step": { "total": 246.04874880098805, "count": 18201, "is_parallel": true, "self": 9.509541083990825, "children": { "UnityEnvironment._generate_step_input": { "total": 5.192690856009676, "count": 18201, "is_parallel": true, "self": 5.192690856009676 }, "communicator.exchange": { "total": 198.39764851198765, "count": 18201, "is_parallel": true, "self": 198.39764851198765 }, "steps_from_proto": { "total": 32.948868348999895, "count": 18201, "is_parallel": true, "self": 6.371701255972539, "children": { "_process_rank_one_or_two_observation": { "total": 26.577167093027356, "count": 182010, "is_parallel": true, "self": 26.577167093027356 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013385600004767184, "count": 1, "self": 0.00013385600004767184, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 499.283321949938, "count": 437737, "is_parallel": true, "self": 9.527853400910544, "children": { "process_trajectory": { "total": 247.60172004002675, "count": 437737, "is_parallel": true, "self": 246.41495982102674, "children": { "RLTrainer._checkpoint": { "total": 1.186760219000007, "count": 4, "is_parallel": true, "self": 1.186760219000007 } } }, "_update_policy": { "total": 242.1537485090007, "count": 90, "is_parallel": true, "self": 67.51354415201263, "children": { "TorchPPOOptimizer.update": { "total": 174.64020435698808, "count": 9177, "is_parallel": true, "self": 174.64020435698808 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14544028499994965, "count": 1, "self": 0.001037149000012505, "children": { "RLTrainer._checkpoint": { "total": 0.14440313599993715, "count": 1, "self": 0.14440313599993715 } } } } } } }