{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9638962149620056, "min": 0.9638962149620056, "max": 2.8604817390441895, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9203.28125, "min": 9203.28125, "max": 29294.193359375, "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": 11.765875816345215, "min": 0.408211350440979, "max": 11.765875816345215, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2294.345703125, "min": 79.19300079345703, "max": 2347.130859375, "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": 0.07031828709937947, "min": 0.06320318615482891, "max": 0.07713230797161505, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2812731483975179, "min": 0.25281274461931563, "max": 0.3702161867640112, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18231537273409318, "min": 0.11992926095548434, "max": 0.27629638704306936, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7292614909363727, "min": 0.47971704382193736, "max": 1.379825735209035, "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": 23.295454545454547, "min": 3.6818181818181817, "max": 23.295454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1025.0, "min": 162.0, "max": 1274.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.295454545454547, "min": 3.6818181818181817, "max": 23.295454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1025.0, "min": 162.0, "max": 1274.0, "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": "1719684379", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719684840" }, "total": 461.00508067199996, "count": 1, "self": 0.4420015840000815, "children": { "run_training.setup": { "total": 0.05804815099997995, "count": 1, "self": 0.05804815099997995 }, "TrainerController.start_learning": { "total": 460.5050309369999, "count": 1, "self": 0.5879718729955812, "children": { "TrainerController._reset_env": { "total": 2.954511751000041, "count": 1, "self": 2.954511751000041 }, "TrainerController.advance": { "total": 456.8746361640042, "count": 18201, "self": 0.29702686899292985, "children": { "env_step": { "total": 456.57760929501126, "count": 18201, "self": 296.82794688501906, "children": { "SubprocessEnvManager._take_step": { "total": 159.45893456599674, "count": 18201, "self": 1.5359172759950752, "children": { "TorchPolicy.evaluate": { "total": 157.92301729000167, "count": 18201, "self": 157.92301729000167 } } }, "workers": { "total": 0.29072784399545526, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 459.2139670870007, "count": 18201, "is_parallel": true, "self": 229.77925387199934, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007047695999972348, "count": 1, "is_parallel": true, "self": 0.00539912299984735, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016485730001249976, "count": 10, "is_parallel": true, "self": 0.0016485730001249976 } } }, "UnityEnvironment.step": { "total": 0.07892860700007986, "count": 1, "is_parallel": true, "self": 0.0007180520001384139, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00032995200001550984, "count": 1, "is_parallel": true, "self": 0.00032995200001550984 }, "communicator.exchange": { "total": 0.0759353649999639, "count": 1, "is_parallel": true, "self": 0.0759353649999639 }, "steps_from_proto": { "total": 0.0019452379999620462, "count": 1, "is_parallel": true, "self": 0.0003668469997819557, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015783910001800905, "count": 10, "is_parallel": true, "self": 0.0015783910001800905 } } } } } } }, "UnityEnvironment.step": { "total": 229.43471321500135, "count": 18200, "is_parallel": true, "self": 10.310564489004264, "children": { "UnityEnvironment._generate_step_input": { "total": 5.333186343002922, "count": 18200, "is_parallel": true, "self": 5.333186343002922 }, "communicator.exchange": { "total": 180.02053162099685, "count": 18200, "is_parallel": true, "self": 180.02053162099685 }, "steps_from_proto": { "total": 33.77043076199732, "count": 18200, "is_parallel": true, "self": 6.469620510989671, "children": { "_process_rank_one_or_two_observation": { "total": 27.300810251007647, "count": 182000, "is_parallel": true, "self": 27.300810251007647 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012859299999945506, "count": 1, "self": 0.00012859299999945506, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 451.18733111903225, "count": 686288, "is_parallel": true, "self": 14.541220140073165, "children": { "process_trajectory": { "total": 250.53824417395901, "count": 686288, "is_parallel": true, "self": 249.88781816495896, "children": { "RLTrainer._checkpoint": { "total": 0.6504260090000571, "count": 4, "is_parallel": true, "self": 0.6504260090000571 } } }, "_update_policy": { "total": 186.10786680500007, "count": 90, "is_parallel": true, "self": 59.099555289003774, "children": { "TorchPPOOptimizer.update": { "total": 127.0083115159963, "count": 4587, "is_parallel": true, "self": 127.0083115159963 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08778255600009288, "count": 1, "self": 0.001138577000119767, "children": { "RLTrainer._checkpoint": { "total": 0.08664397899997311, "count": 1, "self": 0.08664397899997311 } } } } } } }