{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9903442859649658, "min": 0.9903442859649658, "max": 2.862088918685913, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9466.701171875, "min": 9466.701171875, "max": 29342.13671875, "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": 12.788631439208984, "min": 0.5513436198234558, "max": 12.788631439208984, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2493.783203125, "min": 106.96066284179688, "max": 2582.719482421875, "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": 0.06336570251925663, "min": 0.062291953718979096, "max": 0.07988380457205566, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25346281007702653, "min": 0.24916781487591638, "max": 0.3873366560392063, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20610656304394498, "min": 0.1481810764400471, "max": 0.2829183659132789, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8244262521757799, "min": 0.5927243057601884, "max": 1.4145918295663946, "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": 25.522727272727273, "min": 3.977272727272727, "max": 25.522727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1123.0, "min": 175.0, "max": 1386.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.522727272727273, "min": 3.977272727272727, "max": 25.522727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1123.0, "min": 175.0, "max": 1386.0, "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": "1725045224", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725045874" }, "total": 649.739512161, "count": 1, "self": 0.5830127970001513, "children": { "run_training.setup": { "total": 0.07011425899997903, "count": 1, "self": 0.07011425899997903 }, "TrainerController.start_learning": { "total": 649.0863851049999, "count": 1, "self": 0.8990358929931972, "children": { "TrainerController._reset_env": { "total": 2.6586252140000397, "count": 1, "self": 2.6586252140000397 }, "TrainerController.advance": { "total": 645.4401117680065, "count": 18202, "self": 0.45615616601889997, "children": { "env_step": { "total": 644.9839556019876, "count": 18202, "self": 493.72026344297683, "children": { "SubprocessEnvManager._take_step": { "total": 150.8021814079999, "count": 18202, "self": 2.810301476993004, "children": { "TorchPolicy.evaluate": { "total": 147.9918799310069, "count": 18202, "self": 147.9918799310069 } } }, "workers": { "total": 0.46151075101090555, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 647.090464385002, "count": 18202, "is_parallel": true, "self": 307.87685226301176, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026868290000265915, "count": 1, "is_parallel": true, "self": 0.0007343940001192095, "children": { "_process_rank_one_or_two_observation": { "total": 0.001952434999907382, "count": 10, "is_parallel": true, "self": 0.001952434999907382 } } }, "UnityEnvironment.step": { "total": 0.04965448399991601, "count": 1, "is_parallel": true, "self": 0.0007878239997580749, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006494630000588586, "count": 1, "is_parallel": true, "self": 0.0006494630000588586 }, "communicator.exchange": { "total": 0.045658251000077144, "count": 1, "is_parallel": true, "self": 0.045658251000077144 }, "steps_from_proto": { "total": 0.0025589460000219333, "count": 1, "is_parallel": true, "self": 0.000489608000066255, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020693379999556782, "count": 10, "is_parallel": true, "self": 0.0020693379999556782 } } } } } } }, "UnityEnvironment.step": { "total": 339.2136121219902, "count": 18201, "is_parallel": true, "self": 15.412836582011664, "children": { "UnityEnvironment._generate_step_input": { "total": 7.73002835798286, "count": 18201, "is_parallel": true, "self": 7.73002835798286 }, "communicator.exchange": { "total": 268.4631723819982, "count": 18201, "is_parallel": true, "self": 268.4631723819982 }, "steps_from_proto": { "total": 47.60757479999745, "count": 18201, "is_parallel": true, "self": 9.379642761998866, "children": { "_process_rank_one_or_two_observation": { "total": 38.227932037998585, "count": 182010, "is_parallel": true, "self": 38.227932037998585 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003381190001618961, "count": 1, "self": 0.0003381190001618961, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 637.4597724920507, "count": 773789, "is_parallel": true, "self": 20.032490230093458, "children": { "process_trajectory": { "total": 343.9219909679573, "count": 773789, "is_parallel": true, "self": 343.17832610695746, "children": { "RLTrainer._checkpoint": { "total": 0.7436648609998429, "count": 4, "is_parallel": true, "self": 0.7436648609998429 } } }, "_update_policy": { "total": 273.5052912939999, "count": 90, "is_parallel": true, "self": 78.25983720699912, "children": { "TorchPPOOptimizer.update": { "total": 195.24545408700078, "count": 4587, "is_parallel": true, "self": 195.24545408700078 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08827411099991878, "count": 1, "self": 0.001312497000071744, "children": { "RLTrainer._checkpoint": { "total": 0.08696161399984703, "count": 1, "self": 0.08696161399984703 } } } } } } }