{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1287016868591309, "min": 1.1287016868591309, "max": 2.860299587249756, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10789.259765625, "min": 10789.259765625, "max": 29386.71875, "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": 12.56136417388916, "min": 0.42831405997276306, "max": 12.56136417388916, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2449.466064453125, "min": 83.09292602539062, "max": 2518.42626953125, "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": 0.07234614758700071, "min": 0.06346464154447341, "max": 0.07399849729685515, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28938459034800285, "min": 0.25385856617789365, "max": 0.36443283581634295, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19744129559280826, "min": 0.12063336572564189, "max": 0.29417016452141836, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.789765182371233, "min": 0.48253346290256754, "max": 1.411202630283786, "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": 24.568181818181817, "min": 3.25, "max": 24.763636363636362, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1081.0, "min": 143.0, "max": 1362.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.568181818181817, "min": 3.25, "max": 24.763636363636362, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1081.0, "min": 143.0, "max": 1362.0, "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": "1679443947", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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=SnowballTarget1 --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": "1679444433" }, "total": 485.99730680799996, "count": 1, "self": 0.4330716609999854, "children": { "run_training.setup": { "total": 0.1032072200000016, "count": 1, "self": 0.1032072200000016 }, "TrainerController.start_learning": { "total": 485.461027927, "count": 1, "self": 0.6317883499957588, "children": { "TrainerController._reset_env": { "total": 9.17120914200001, "count": 1, "self": 9.17120914200001 }, "TrainerController.advance": { "total": 475.5222376590042, "count": 18203, "self": 0.3480923360105521, "children": { "env_step": { "total": 475.17414532299364, "count": 18203, "self": 344.50612449499175, "children": { "SubprocessEnvManager._take_step": { "total": 130.3560956640016, "count": 18203, "self": 2.261910032988567, "children": { "TorchPolicy.evaluate": { "total": 128.09418563101303, "count": 18203, "self": 128.09418563101303 } } }, "workers": { "total": 0.3119251640002858, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 483.73482235600386, "count": 18203, "is_parallel": true, "self": 225.47895240000406, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004748722999977417, "count": 1, "is_parallel": true, "self": 0.0033297160000529402, "children": { "_process_rank_one_or_two_observation": { "total": 0.001419006999924477, "count": 10, "is_parallel": true, "self": 0.001419006999924477 } } }, "UnityEnvironment.step": { "total": 0.04288157499996714, "count": 1, "is_parallel": true, "self": 0.00037039699998331344, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002945269999941047, "count": 1, "is_parallel": true, "self": 0.0002945269999941047 }, "communicator.exchange": { "total": 0.040340876000016124, "count": 1, "is_parallel": true, "self": 0.040340876000016124 }, "steps_from_proto": { "total": 0.0018757749999736006, "count": 1, "is_parallel": true, "self": 0.00037448599994149845, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015012890000321022, "count": 10, "is_parallel": true, "self": 0.0015012890000321022 } } } } } } }, "UnityEnvironment.step": { "total": 258.2558699559998, "count": 18202, "is_parallel": true, "self": 9.824119722009641, "children": { "UnityEnvironment._generate_step_input": { "total": 5.350957151003513, "count": 18202, "is_parallel": true, "self": 5.350957151003513 }, "communicator.exchange": { "total": 210.47536818398862, "count": 18202, "is_parallel": true, "self": 210.47536818398862 }, "steps_from_proto": { "total": 32.605424898998024, "count": 18202, "is_parallel": true, "self": 6.73990881399385, "children": { "_process_rank_one_or_two_observation": { "total": 25.865516085004174, "count": 182020, "is_parallel": true, "self": 25.865516085004174 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015246600003138155, "count": 1, "self": 0.00015246600003138155, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 471.8537700099765, "count": 439635, "is_parallel": true, "self": 10.508469179973986, "children": { "process_trajectory": { "total": 263.73302482300255, "count": 439635, "is_parallel": true, "self": 262.8425930390026, "children": { "RLTrainer._checkpoint": { "total": 0.8904317839999294, "count": 4, "is_parallel": true, "self": 0.8904317839999294 } } }, "_update_policy": { "total": 197.61227600699993, "count": 90, "is_parallel": true, "self": 69.84085060100011, "children": { "TorchPPOOptimizer.update": { "total": 127.77142540599982, "count": 4587, "is_parallel": true, "self": 127.77142540599982 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13564030999998522, "count": 1, "self": 0.0008952059999955964, "children": { "RLTrainer._checkpoint": { "total": 0.13474510399998962, "count": 1, "self": 0.13474510399998962 } } } } } } }