{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8937958478927612, "min": 0.8937958478927612, "max": 2.8560962677001953, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8524.130859375, "min": 8524.130859375, "max": 29249.28125, "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": 13.011703491210938, "min": 0.4500361680984497, "max": 13.011703491210938, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2537.2822265625, "min": 87.30701446533203, "max": 2649.14599609375, "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": 0.06854830959748463, "min": 0.06291104920027839, "max": 0.0778961117766277, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27419323838993853, "min": 0.25164419680111355, "max": 0.38231461524264887, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18018287135397687, "min": 0.11469312888163817, "max": 0.2701711751082364, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7207314854159075, "min": 0.4587725155265527, "max": 1.321306158514584, "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": 25.045454545454547, "min": 3.159090909090909, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1102.0, "min": 139.0, "max": 1425.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.045454545454547, "min": 3.159090909090909, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1102.0, "min": 139.0, "max": 1425.0, "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": "1712027324", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712027747" }, "total": 423.0662878300001, "count": 1, "self": 0.43301932899987605, "children": { "run_training.setup": { "total": 0.054953421000050184, "count": 1, "self": 0.054953421000050184 }, "TrainerController.start_learning": { "total": 422.57831508000015, "count": 1, "self": 0.49907296099377163, "children": { "TrainerController._reset_env": { "total": 2.9382136540000374, "count": 1, "self": 2.9382136540000374 }, "TrainerController.advance": { "total": 419.05247626300627, "count": 18199, "self": 0.23912888301310886, "children": { "env_step": { "total": 418.81334737999316, "count": 18199, "self": 267.81089763498983, "children": { "SubprocessEnvManager._take_step": { "total": 150.75001012301198, "count": 18199, "self": 1.3762942330001806, "children": { "TorchPolicy.evaluate": { "total": 149.3737158900118, "count": 18199, "self": 149.3737158900118 } } }, "workers": { "total": 0.25243962199135694, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 421.5374383059924, "count": 18199, "is_parallel": true, "self": 212.58035622897876, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007822805000046174, "count": 1, "is_parallel": true, "self": 0.00377668599981007, "children": { "_process_rank_one_or_two_observation": { "total": 0.004046119000236104, "count": 10, "is_parallel": true, "self": 0.004046119000236104 } } }, "UnityEnvironment.step": { "total": 0.03933985499998016, "count": 1, "is_parallel": true, "self": 0.00069160699990789, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041636000003109075, "count": 1, "is_parallel": true, "self": 0.00041636000003109075 }, "communicator.exchange": { "total": 0.03626234099999692, "count": 1, "is_parallel": true, "self": 0.03626234099999692 }, "steps_from_proto": { "total": 0.0019695470000442583, "count": 1, "is_parallel": true, "self": 0.00038123399997402885, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015883130000702295, "count": 10, "is_parallel": true, "self": 0.0015883130000702295 } } } } } } }, "UnityEnvironment.step": { "total": 208.95708207701364, "count": 18198, "is_parallel": true, "self": 9.904045724021785, "children": { "UnityEnvironment._generate_step_input": { "total": 5.157691507984623, "count": 18198, "is_parallel": true, "self": 5.157691507984623 }, "communicator.exchange": { "total": 161.86490850699454, "count": 18198, "is_parallel": true, "self": 161.86490850699454 }, "steps_from_proto": { "total": 32.03043633801269, "count": 18198, "is_parallel": true, "self": 5.85992971399412, "children": { "_process_rank_one_or_two_observation": { "total": 26.17050662401857, "count": 181980, "is_parallel": true, "self": 26.17050662401857 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013793700009046006, "count": 1, "self": 0.00013793700009046006, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 413.6591491481407, "count": 653819, "is_parallel": true, "self": 13.487534219995041, "children": { "process_trajectory": { "total": 228.66555477914653, "count": 653819, "is_parallel": true, "self": 228.08294792514664, "children": { "RLTrainer._checkpoint": { "total": 0.5826068539998914, "count": 4, "is_parallel": true, "self": 0.5826068539998914 } } }, "_update_policy": { "total": 171.50606014899915, "count": 90, "is_parallel": true, "self": 49.400389155997345, "children": { "TorchPPOOptimizer.update": { "total": 122.10567099300181, "count": 4587, "is_parallel": true, "self": 122.10567099300181 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08841426499998306, "count": 1, "self": 0.0009823239997786004, "children": { "RLTrainer._checkpoint": { "total": 0.08743194100020446, "count": 1, "self": 0.08743194100020446 } } } } } } }