{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8287274241447449, "min": 0.826555609703064, "max": 2.8573737144470215, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7921.80517578125, "min": 7921.80517578125, "max": 29262.36328125, "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": 12.982161521911621, "min": 0.40781259536743164, "max": 13.045551300048828, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2531.521484375, "min": 79.11564636230469, "max": 2661.29248046875, "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": 0.06452847795951717, "min": 0.0611421328420179, "max": 0.07841257712205726, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2581139118380687, "min": 0.2445685313680716, "max": 0.3920628856102863, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21123789586857253, "min": 0.12963554869730062, "max": 0.271372680570565, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8449515834742901, "min": 0.5185421947892025, "max": 1.3266558965631559, "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": 24.977272727272727, "min": 3.590909090909091, "max": 25.6, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 158.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 3.590909090909091, "max": 25.6, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 158.0, "max": 1408.0, "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": "1715106373", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715106834" }, "total": 460.846785631, "count": 1, "self": 0.4358575910000013, "children": { "run_training.setup": { "total": 0.055608195999980126, "count": 1, "self": 0.055608195999980126 }, "TrainerController.start_learning": { "total": 460.355319844, "count": 1, "self": 0.5750492310091886, "children": { "TrainerController._reset_env": { "total": 2.9000364109999737, "count": 1, "self": 2.9000364109999737 }, "TrainerController.advance": { "total": 456.7867670409909, "count": 18212, "self": 0.2734104389919594, "children": { "env_step": { "total": 456.51335660199896, "count": 18212, "self": 293.09724741900516, "children": { "SubprocessEnvManager._take_step": { "total": 163.1213200499966, "count": 18212, "self": 1.5621526779983128, "children": { "TorchPolicy.evaluate": { "total": 161.55916737199829, "count": 18212, "self": 161.55916737199829 } } }, "workers": { "total": 0.29478913299720944, "count": 18212, "self": 0.0, "children": { "worker_root": { "total": 459.10804589999793, "count": 18212, "is_parallel": true, "self": 231.6976893109936, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005957021999961398, "count": 1, "is_parallel": true, "self": 0.004210250999960863, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017467710000005354, "count": 10, "is_parallel": true, "self": 0.0017467710000005354 } } }, "UnityEnvironment.step": { "total": 0.1120908070000155, "count": 1, "is_parallel": true, "self": 0.0006722480000007636, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039912900001581875, "count": 1, "is_parallel": true, "self": 0.00039912900001581875 }, "communicator.exchange": { "total": 0.10900379100002056, "count": 1, "is_parallel": true, "self": 0.10900379100002056 }, "steps_from_proto": { "total": 0.002015638999978364, "count": 1, "is_parallel": true, "self": 0.00036226600002464693, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016533729999537172, "count": 10, "is_parallel": true, "self": 0.0016533729999537172 } } } } } } }, "UnityEnvironment.step": { "total": 227.41035658900432, "count": 18211, "is_parallel": true, "self": 10.566459893999252, "children": { "UnityEnvironment._generate_step_input": { "total": 5.7627427230041235, "count": 18211, "is_parallel": true, "self": 5.7627427230041235 }, "communicator.exchange": { "total": 175.289007928001, "count": 18211, "is_parallel": true, "self": 175.289007928001 }, "steps_from_proto": { "total": 35.792146043999935, "count": 18211, "is_parallel": true, "self": 6.659214950001399, "children": { "_process_rank_one_or_two_observation": { "total": 29.132931093998536, "count": 182110, "is_parallel": true, "self": 29.132931093998536 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019678499995734455, "count": 1, "self": 0.00019678499995734455, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 450.9477390709713, "count": 690623, "is_parallel": true, "self": 15.002527576008504, "children": { "process_trajectory": { "total": 249.81069508196282, "count": 690623, "is_parallel": true, "self": 248.79508281596281, "children": { "RLTrainer._checkpoint": { "total": 1.015612266000005, "count": 4, "is_parallel": true, "self": 1.015612266000005 } } }, "_update_policy": { "total": 186.13451641299997, "count": 90, "is_parallel": true, "self": 52.96658783199604, "children": { "TorchPPOOptimizer.update": { "total": 133.16792858100393, "count": 4584, "is_parallel": true, "self": 133.16792858100393 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09327037599996402, "count": 1, "self": 0.0009769299999788927, "children": { "RLTrainer._checkpoint": { "total": 0.09229344599998512, "count": 1, "self": 0.09229344599998512 } } } } } } }