{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8960548639297485, "min": 0.8960548639297485, "max": 2.869885206222534, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8565.388671875, "min": 8565.388671875, "max": 29422.0625, "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": 12.859189987182617, "min": 0.3713598847389221, "max": 12.859189987182617, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2507.5419921875, "min": 72.04381561279297, "max": 2619.029296875, "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": 0.07028828269568632, "min": 0.0614336508328515, "max": 0.07886927928570112, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2811531307827453, "min": 0.2660193043172031, "max": 0.36066695561577733, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20297336987420625, "min": 0.12472591794999865, "max": 0.2695046321434133, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.811893479496825, "min": 0.4989036717999946, "max": 1.3049346608858483, "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": 3.340909090909091, "max": 25.472727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 147.0, "max": 1401.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 3.340909090909091, "max": 25.472727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 147.0, "max": 1401.0, "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": "1679241243", "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": "1679241716" }, "total": 473.029216024, "count": 1, "self": 0.7097565850000365, "children": { "run_training.setup": { "total": 0.10939874799998961, "count": 1, "self": 0.10939874799998961 }, "TrainerController.start_learning": { "total": 472.21006069099997, "count": 1, "self": 0.6098321860019951, "children": { "TrainerController._reset_env": { "total": 9.240619820999996, "count": 1, "self": 9.240619820999996 }, "TrainerController.advance": { "total": 462.15221049499803, "count": 18222, "self": 0.3006127089952315, "children": { "env_step": { "total": 461.8515977860028, "count": 18222, "self": 334.2911683039905, "children": { "SubprocessEnvManager._take_step": { "total": 127.27447324300852, "count": 18222, "self": 2.1553303590023916, "children": { "TorchPolicy.evaluate": { "total": 125.11914288400612, "count": 18222, "self": 125.11914288400612 } } }, "workers": { "total": 0.28595623900378087, "count": 18222, "self": 0.0, "children": { "worker_root": { "total": 470.39188831300476, "count": 18222, "is_parallel": true, "self": 222.0362497080116, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005369237999957477, "count": 1, "is_parallel": true, "self": 0.003808698999932858, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015605390000246189, "count": 10, "is_parallel": true, "self": 0.0015605390000246189 } } }, "UnityEnvironment.step": { "total": 0.08818202399993424, "count": 1, "is_parallel": true, "self": 0.0005287280000629835, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034746999995149963, "count": 1, "is_parallel": true, "self": 0.00034746999995149963 }, "communicator.exchange": { "total": 0.08554308399993715, "count": 1, "is_parallel": true, "self": 0.08554308399993715 }, "steps_from_proto": { "total": 0.0017627419999826088, "count": 1, "is_parallel": true, "self": 0.00036885799988795043, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013938840000946584, "count": 10, "is_parallel": true, "self": 0.0013938840000946584 } } } } } } }, "UnityEnvironment.step": { "total": 248.35563860499315, "count": 18221, "is_parallel": true, "self": 9.624626135968242, "children": { "UnityEnvironment._generate_step_input": { "total": 5.2576775330052214, "count": 18221, "is_parallel": true, "self": 5.2576775330052214 }, "communicator.exchange": { "total": 201.6842496700142, "count": 18221, "is_parallel": true, "self": 201.6842496700142 }, "steps_from_proto": { "total": 31.789085266005486, "count": 18221, "is_parallel": true, "self": 6.423761049997779, "children": { "_process_rank_one_or_two_observation": { "total": 25.365324216007707, "count": 182210, "is_parallel": true, "self": 25.365324216007707 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013270299996293033, "count": 1, "self": 0.00013270299996293033, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 458.73458260902635, "count": 423862, "is_parallel": true, "self": 10.03053322103392, "children": { "process_trajectory": { "total": 256.2406376609928, "count": 423862, "is_parallel": true, "self": 254.78627317399275, "children": { "RLTrainer._checkpoint": { "total": 1.4543644870000207, "count": 4, "is_parallel": true, "self": 1.4543644870000207 } } }, "_update_policy": { "total": 192.46341172699965, "count": 90, "is_parallel": true, "self": 69.78314754699682, "children": { "TorchPPOOptimizer.update": { "total": 122.68026418000284, "count": 4587, "is_parallel": true, "self": 122.68026418000284 } } } } } } } } }, "TrainerController._save_models": { "total": 0.20726548599998296, "count": 1, "self": 0.001103405999970164, "children": { "RLTrainer._checkpoint": { "total": 0.2061620800000128, "count": 1, "self": 0.2061620800000128 } } } } } } }