{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0273736715316772, "min": 1.0273736715316772, "max": 2.8761963844299316, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9809.36328125, "min": 9809.36328125, "max": 29486.765625, "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": 12.962425231933594, "min": 0.2534676492214203, "max": 12.962425231933594, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2527.6728515625, "min": 49.172725677490234, "max": 2606.60791015625, "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": 0.07032245017206365, "min": 0.06528018078967637, "max": 0.07327674707333905, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2812898006882546, "min": 0.2645933747168302, "max": 0.3663837353666952, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1970665380358696, "min": 0.10647535229708963, "max": 0.28842396216065275, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7882661521434784, "min": 0.4259014091883585, "max": 1.416002262748924, "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": 25.613636363636363, "min": 3.0454545454545454, "max": 25.613636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1127.0, "min": 134.0, "max": 1370.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.613636363636363, "min": 3.0454545454545454, "max": 25.613636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1127.0, "min": 134.0, "max": 1370.0, "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": "1678907245", "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": "1678907714" }, "total": 469.286838568, "count": 1, "self": 0.43509517500001493, "children": { "run_training.setup": { "total": 0.18169876199999635, "count": 1, "self": 0.18169876199999635 }, "TrainerController.start_learning": { "total": 468.670044631, "count": 1, "self": 0.5750117690001275, "children": { "TrainerController._reset_env": { "total": 8.44552257700002, "count": 1, "self": 8.44552257700002 }, "TrainerController.advance": { "total": 459.51334908099983, "count": 18201, "self": 0.28581167000641017, "children": { "env_step": { "total": 459.2275374109934, "count": 18201, "self": 330.7172023179776, "children": { "SubprocessEnvManager._take_step": { "total": 128.23284132900193, "count": 18201, "self": 2.068288839991226, "children": { "TorchPolicy.evaluate": { "total": 126.1645524890107, "count": 18201, "self": 126.1645524890107 } } }, "workers": { "total": 0.27749376401391146, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 467.2351463169953, "count": 18201, "is_parallel": true, "self": 221.35111302199533, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0058084780000058345, "count": 1, "is_parallel": true, "self": 0.004199190999997882, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016092870000079529, "count": 10, "is_parallel": true, "self": 0.0016092870000079529 } } }, "UnityEnvironment.step": { "total": 0.051360861000034674, "count": 1, "is_parallel": true, "self": 0.0037873570000215295, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003993999999920561, "count": 1, "is_parallel": true, "self": 0.0003993999999920561 }, "communicator.exchange": { "total": 0.04521996900001568, "count": 1, "is_parallel": true, "self": 0.04521996900001568 }, "steps_from_proto": { "total": 0.001954135000005408, "count": 1, "is_parallel": true, "self": 0.0003967609999904198, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015573740000149883, "count": 10, "is_parallel": true, "self": 0.0015573740000149883 } } } } } } }, "UnityEnvironment.step": { "total": 245.884033295, "count": 18200, "is_parallel": true, "self": 9.706542587005572, "children": { "UnityEnvironment._generate_step_input": { "total": 5.37257240100007, "count": 18200, "is_parallel": true, "self": 5.37257240100007 }, "communicator.exchange": { "total": 198.27650285699696, "count": 18200, "is_parallel": true, "self": 198.27650285699696 }, "steps_from_proto": { "total": 32.5284154499974, "count": 18200, "is_parallel": true, "self": 6.506366868979796, "children": { "_process_rank_one_or_two_observation": { "total": 26.0220485810176, "count": 182000, "is_parallel": true, "self": 26.0220485810176 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012082699993243295, "count": 1, "self": 0.00012082699993243295, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 456.14905428200603, "count": 407369, "is_parallel": true, "self": 10.040476226018143, "children": { "process_trajectory": { "total": 254.18717188598754, "count": 407369, "is_parallel": true, "self": 252.95841491298762, "children": { "RLTrainer._checkpoint": { "total": 1.2287569729999177, "count": 4, "is_parallel": true, "self": 1.2287569729999177 } } }, "_update_policy": { "total": 191.92140617000035, "count": 90, "is_parallel": true, "self": 70.0075620379991, "children": { "TorchPPOOptimizer.update": { "total": 121.91384413200126, "count": 4587, "is_parallel": true, "self": 121.91384413200126 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13604037700008575, "count": 1, "self": 0.0009082220001346286, "children": { "RLTrainer._checkpoint": { "total": 0.13513215499995113, "count": 1, "self": 0.13513215499995113 } } } } } } }