{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9803673624992371, "min": 0.9803673624992371, "max": 2.8621463775634766, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9349.763671875, "min": 9349.763671875, "max": 29563.109375, "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": 11.90688705444336, "min": 0.33911290764808655, "max": 11.90688705444336, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2321.843017578125, "min": 65.78790283203125, "max": 2385.557861328125, "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": 0.06886074343735042, "min": 0.06283497967638586, "max": 0.07325382568210355, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2754429737494017, "min": 0.25133991870554345, "max": 0.36626912841051773, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19011121834902203, "min": 0.12019623160663553, "max": 0.2775002205926998, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7604448733960881, "min": 0.48078492642654214, "max": 1.374064699399705, "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": 23.818181818181817, "min": 3.090909090909091, "max": 23.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1048.0, "min": 136.0, "max": 1284.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.818181818181817, "min": 3.090909090909091, "max": 23.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1048.0, "min": 136.0, "max": 1284.0, "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": "1701685590", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701686079" }, "total": 489.48266912, "count": 1, "self": 0.7460992499999861, "children": { "run_training.setup": { "total": 0.06035600699999577, "count": 1, "self": 0.06035600699999577 }, "TrainerController.start_learning": { "total": 488.67621386300004, "count": 1, "self": 0.5826083869926606, "children": { "TrainerController._reset_env": { "total": 4.538193275000026, "count": 1, "self": 4.538193275000026 }, "TrainerController.advance": { "total": 483.42577634100735, "count": 18211, "self": 0.2762179720056679, "children": { "env_step": { "total": 483.1495583690017, "count": 18211, "self": 328.68681239499824, "children": { "SubprocessEnvManager._take_step": { "total": 154.16755047799757, "count": 18211, "self": 1.5037028399996757, "children": { "TorchPolicy.evaluate": { "total": 152.6638476379979, "count": 18211, "self": 152.6638476379979 } } }, "workers": { "total": 0.29519549600587425, "count": 18211, "self": 0.0, "children": { "worker_root": { "total": 487.22954101698923, "count": 18211, "is_parallel": true, "self": 238.41782910799304, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005836934999990717, "count": 1, "is_parallel": true, "self": 0.003774838000026648, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020620969999640693, "count": 10, "is_parallel": true, "self": 0.0020620969999640693 } } }, "UnityEnvironment.step": { "total": 0.035156537999966986, "count": 1, "is_parallel": true, "self": 0.0007280359999981556, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043996300001936106, "count": 1, "is_parallel": true, "self": 0.00043996300001936106 }, "communicator.exchange": { "total": 0.03200818599998456, "count": 1, "is_parallel": true, "self": 0.03200818599998456 }, "steps_from_proto": { "total": 0.001980352999964907, "count": 1, "is_parallel": true, "self": 0.00038471699991760033, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015956360000473069, "count": 10, "is_parallel": true, "self": 0.0015956360000473069 } } } } } } }, "UnityEnvironment.step": { "total": 248.8117119089962, "count": 18210, "is_parallel": true, "self": 10.813222700992242, "children": { "UnityEnvironment._generate_step_input": { "total": 5.508286935005174, "count": 18210, "is_parallel": true, "self": 5.508286935005174 }, "communicator.exchange": { "total": 197.70515340199756, "count": 18210, "is_parallel": true, "self": 197.70515340199756 }, "steps_from_proto": { "total": 34.78504887100121, "count": 18210, "is_parallel": true, "self": 6.52728339997725, "children": { "_process_rank_one_or_two_observation": { "total": 28.25776547102396, "count": 182100, "is_parallel": true, "self": 28.25776547102396 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017749400001321192, "count": 1, "self": 0.00017749400001321192, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 479.320645972972, "count": 509087, "is_parallel": true, "self": 10.990395558951548, "children": { "process_trajectory": { "total": 271.15939651002105, "count": 509087, "is_parallel": true, "self": 270.33041718802116, "children": { "RLTrainer._checkpoint": { "total": 0.8289793219998955, "count": 4, "is_parallel": true, "self": 0.8289793219998955 } } }, "_update_policy": { "total": 197.1708539039994, "count": 90, "is_parallel": true, "self": 60.016544971998826, "children": { "TorchPPOOptimizer.update": { "total": 137.15430893200056, "count": 4587, "is_parallel": true, "self": 137.15430893200056 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12945836599999438, "count": 1, "self": 0.0011502119999704519, "children": { "RLTrainer._checkpoint": { "total": 0.12830815400002393, "count": 1, "self": 0.12830815400002393 } } } } } } }