{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8380652070045471, "min": 0.8380652070045471, "max": 2.86793851852417, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7992.6279296875, "min": 7992.6279296875, "max": 29465.19921875, "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": 13.224584579467773, "min": 0.3086864948272705, "max": 13.224584579467773, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2578.7939453125, "min": 59.88518142700195, "max": 2662.65234375, "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": 0.06429870069105699, "min": 0.06305158233068034, "max": 0.07688703273557693, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25719480276422796, "min": 0.25719480276422796, "max": 0.3680479179967341, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22320427007827107, "min": 0.11724227503873408, "max": 0.2887334205940658, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8928170803130843, "min": 0.4689691001549363, "max": 1.443667102970329, "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": 26.15909090909091, "min": 2.9318181818181817, "max": 26.15909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1151.0, "min": 129.0, "max": 1415.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.15909090909091, "min": 2.9318181818181817, "max": 26.15909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1151.0, "min": 129.0, "max": 1415.0, "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": "1696844406", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1696844911" }, "total": 505.03822517900016, "count": 1, "self": 0.4776659260000997, "children": { "run_training.setup": { "total": 0.04718278000018472, "count": 1, "self": 0.04718278000018472 }, "TrainerController.start_learning": { "total": 504.5133764729999, "count": 1, "self": 0.5960175540076307, "children": { "TrainerController._reset_env": { "total": 2.7479221799999323, "count": 1, "self": 2.7479221799999323 }, "TrainerController.advance": { "total": 501.0585141429924, "count": 18199, "self": 0.2848248720083575, "children": { "env_step": { "total": 500.77368927098405, "count": 18199, "self": 348.80038766103644, "children": { "SubprocessEnvManager._take_step": { "total": 151.66969837397755, "count": 18199, "self": 1.5725144779603397, "children": { "TorchPolicy.evaluate": { "total": 150.0971838960172, "count": 18199, "self": 150.0971838960172 } } }, "workers": { "total": 0.30360323597005845, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 503.0740312010198, "count": 18199, "is_parallel": true, "self": 242.95745404798163, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021468390000336512, "count": 1, "is_parallel": true, "self": 0.0006801250005992188, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014667139994344325, "count": 10, "is_parallel": true, "self": 0.0014667139994344325 } } }, "UnityEnvironment.step": { "total": 0.05079174899992722, "count": 1, "is_parallel": true, "self": 0.000740149999728601, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036704100011775154, "count": 1, "is_parallel": true, "self": 0.00036704100011775154 }, "communicator.exchange": { "total": 0.047455727999931696, "count": 1, "is_parallel": true, "self": 0.047455727999931696 }, "steps_from_proto": { "total": 0.0022288300001491734, "count": 1, "is_parallel": true, "self": 0.00039448599909519544, "children": { "_process_rank_one_or_two_observation": { "total": 0.001834344001053978, "count": 10, "is_parallel": true, "self": 0.001834344001053978 } } } } } } }, "UnityEnvironment.step": { "total": 260.1165771530382, "count": 18198, "is_parallel": true, "self": 11.047466272055317, "children": { "UnityEnvironment._generate_step_input": { "total": 5.658946054993066, "count": 18198, "is_parallel": true, "self": 5.658946054993066 }, "communicator.exchange": { "total": 203.32870648199378, "count": 18198, "is_parallel": true, "self": 203.32870648199378 }, "steps_from_proto": { "total": 40.08145834399602, "count": 18198, "is_parallel": true, "self": 7.478995753892832, "children": { "_process_rank_one_or_two_observation": { "total": 32.60246259010319, "count": 181980, "is_parallel": true, "self": 32.60246259010319 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016169299988177954, "count": 1, "self": 0.00016169299988177954, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 496.927720721078, "count": 506091, "is_parallel": true, "self": 11.041573937968224, "children": { "process_trajectory": { "total": 274.7424503751081, "count": 506091, "is_parallel": true, "self": 273.56809703310773, "children": { "RLTrainer._checkpoint": { "total": 1.1743533420003587, "count": 4, "is_parallel": true, "self": 1.1743533420003587 } } }, "_update_policy": { "total": 211.1436964080017, "count": 90, "is_parallel": true, "self": 83.92297709600052, "children": { "TorchPPOOptimizer.update": { "total": 127.22071931200117, "count": 4587, "is_parallel": true, "self": 127.22071931200117 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11076090300002761, "count": 1, "self": 0.0011854920003315783, "children": { "RLTrainer._checkpoint": { "total": 0.10957541099969603, "count": 1, "self": 0.10957541099969603 } } } } } } }