{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.47499418258667, "min": 1.4670100212097168, "max": 2.8893232345581055, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 14131.9189453125, "min": 14131.9189453125, "max": 29684.90625, "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": 8.433154106140137, "min": 0.5690317749977112, "max": 8.433154106140137, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1644.465087890625, "min": 110.39216613769531, "max": 1683.020263671875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.013796482521987247, "min": 0.011122960411012173, "max": 0.024610452140526227, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.05518593008794899, "min": 0.05518593008794899, "max": 0.11140501078140612, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2847995844980081, "min": 0.13623907572279373, "max": 0.3362031939129035, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.1391983379920323, "min": 0.5449563028911749, "max": 1.5885935028394065, "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": 0.10269400000000001, "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": 0.00014443060000000012, "min": 0.00014443060000000012, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000005, "min": 0.0005777224000000005, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 16.227272727272727, "min": 3.25, "max": 16.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 714.0, "min": 143.0, "max": 920.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 16.227272727272727, "min": 3.25, "max": 16.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 714.0, "min": 143.0, "max": 920.0, "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": "1678957138", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/ckahmann/miniconda3/envs/reinforcementlearning/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678957558" }, "total": 419.84819495584816, "count": 1, "self": 0.2699372051283717, "children": { "run_training.setup": { "total": 0.013312438502907753, "count": 1, "self": 0.013312438502907753 }, "TrainerController.start_learning": { "total": 419.5649453122169, "count": 1, "self": 0.5316747557371855, "children": { "TrainerController._reset_env": { "total": 2.1339439768344164, "count": 1, "self": 2.1339439768344164 }, "TrainerController.advance": { "total": 416.7881746189669, "count": 18203, "self": 0.2367285778746009, "children": { "env_step": { "total": 416.5514460410923, "count": 18203, "self": 310.9145820736885, "children": { "SubprocessEnvManager._take_step": { "total": 105.39318056683987, "count": 18203, "self": 1.3368838606402278, "children": { "TorchPolicy.evaluate": { "total": 104.05629670619965, "count": 18203, "self": 104.05629670619965 } } }, "workers": { "total": 0.2436834005638957, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 418.537881789729, "count": 18203, "is_parallel": true, "self": 140.7538351500407, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0032340725883841515, "count": 1, "is_parallel": true, "self": 0.0008471105247735977, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023869620636105537, "count": 10, "is_parallel": true, "self": 0.0023869620636105537 } } }, "UnityEnvironment.step": { "total": 0.031425817869603634, "count": 1, "is_parallel": true, "self": 0.0008721193298697472, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047319289296865463, "count": 1, "is_parallel": true, "self": 0.00047319289296865463 }, "communicator.exchange": { "total": 0.027380683459341526, "count": 1, "is_parallel": true, "self": 0.027380683459341526 }, "steps_from_proto": { "total": 0.002699822187423706, "count": 1, "is_parallel": true, "self": 0.000547376461327076, "children": { "_process_rank_one_or_two_observation": { "total": 0.00215244572609663, "count": 10, "is_parallel": true, "self": 0.00215244572609663 } } } } } } }, "UnityEnvironment.step": { "total": 277.7840466396883, "count": 18202, "is_parallel": true, "self": 11.949201308190823, "children": { "UnityEnvironment._generate_step_input": { "total": 6.642146414145827, "count": 18202, "is_parallel": true, "self": 6.642146414145827 }, "communicator.exchange": { "total": 221.8610559767112, "count": 18202, "is_parallel": true, "self": 221.8610559767112 }, "steps_from_proto": { "total": 37.33164294064045, "count": 18202, "is_parallel": true, "self": 7.291973237879574, "children": { "_process_rank_one_or_two_observation": { "total": 30.039669702760875, "count": 182020, "is_parallel": true, "self": 30.039669702760875 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019178912043571472, "count": 1, "self": 0.00019178912043571472, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 413.36004654783756, "count": 478254, "is_parallel": true, "self": 9.259764566086233, "children": { "process_trajectory": { "total": 300.5415443768725, "count": 478254, "is_parallel": true, "self": 299.77293086610734, "children": { "RLTrainer._checkpoint": { "total": 0.7686135107651353, "count": 4, "is_parallel": true, "self": 0.7686135107651353 } } }, "_update_policy": { "total": 103.55873760487884, "count": 90, "is_parallel": true, "self": 35.29287077393383, "children": { "TorchPPOOptimizer.update": { "total": 68.26586683094501, "count": 540, "is_parallel": true, "self": 68.26586683094501 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1109601715579629, "count": 1, "self": 0.000704597681760788, "children": { "RLTrainer._checkpoint": { "total": 0.1102555738762021, "count": 1, "self": 0.1102555738762021 } } } } } } }