{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0918282270431519, "min": 1.0918282270431519, "max": 2.864292860031128, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10460.806640625, "min": 10460.806640625, "max": 29364.73046875, "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": 12.482878684997559, "min": 0.4086538851261139, "max": 12.482878684997559, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2434.161376953125, "min": 79.27885437011719, "max": 2519.029541015625, "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": 0.06826546674625099, "min": 0.06202288362135946, "max": 0.07622451220009037, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27306186698500395, "min": 0.24809153448543783, "max": 0.38112256100045183, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21664549673304836, "min": 0.11118768314561606, "max": 0.28863664941460476, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8665819869321935, "min": 0.4447507325824642, "max": 1.443183247073024, "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": 24.15909090909091, "min": 3.25, "max": 24.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1063.0, "min": 143.0, "max": 1365.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.15909090909091, "min": 3.25, "max": 24.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1063.0, "min": 143.0, "max": 1365.0, "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": "1681872082", "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": "1681872529" }, "total": 446.9234556150001, "count": 1, "self": 0.43634499699999196, "children": { "run_training.setup": { "total": 0.11340125600008832, "count": 1, "self": 0.11340125600008832 }, "TrainerController.start_learning": { "total": 446.373709362, "count": 1, "self": 0.5323554089968638, "children": { "TrainerController._reset_env": { "total": 3.923924478999993, "count": 1, "self": 3.923924478999993 }, "TrainerController.advance": { "total": 441.78317691000314, "count": 18204, "self": 0.2592886300012651, "children": { "env_step": { "total": 441.52388828000187, "count": 18204, "self": 322.73706717798734, "children": { "SubprocessEnvManager._take_step": { "total": 118.53707004400405, "count": 18204, "self": 1.7064327490085134, "children": { "TorchPolicy.evaluate": { "total": 116.83063729499554, "count": 18204, "self": 116.83063729499554 } } }, "workers": { "total": 0.24975105801047448, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 444.91341446400463, "count": 18204, "is_parallel": true, "self": 206.54476538501171, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004906232999928761, "count": 1, "is_parallel": true, "self": 0.0034706989995356707, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014355340003930905, "count": 10, "is_parallel": true, "self": 0.0014355340003930905 } } }, "UnityEnvironment.step": { "total": 0.03660663300001943, "count": 1, "is_parallel": true, "self": 0.0005472850000387552, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044618999993417674, "count": 1, "is_parallel": true, "self": 0.00044618999993417674 }, "communicator.exchange": { "total": 0.03329528200004006, "count": 1, "is_parallel": true, "self": 0.03329528200004006 }, "steps_from_proto": { "total": 0.002317876000006436, "count": 1, "is_parallel": true, "self": 0.0004650579999179172, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018528180000885186, "count": 10, "is_parallel": true, "self": 0.0018528180000885186 } } } } } } }, "UnityEnvironment.step": { "total": 238.36864907899292, "count": 18203, "is_parallel": true, "self": 9.754622523988019, "children": { "UnityEnvironment._generate_step_input": { "total": 5.296242678006138, "count": 18203, "is_parallel": true, "self": 5.296242678006138 }, "communicator.exchange": { "total": 192.65159151199805, "count": 18203, "is_parallel": true, "self": 192.65159151199805 }, "steps_from_proto": { "total": 30.66619236500071, "count": 18203, "is_parallel": true, "self": 6.01605793799979, "children": { "_process_rank_one_or_two_observation": { "total": 24.65013442700092, "count": 182030, "is_parallel": true, "self": 24.65013442700092 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013152599990462477, "count": 1, "self": 0.00013152599990462477, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 438.23076522496694, "count": 397472, "is_parallel": true, "self": 9.693771611967463, "children": { "process_trajectory": { "total": 242.38667406899913, "count": 397472, "is_parallel": true, "self": 241.1877967809993, "children": { "RLTrainer._checkpoint": { "total": 1.198877287999835, "count": 4, "is_parallel": true, "self": 1.198877287999835 } } }, "_update_policy": { "total": 186.15031954400035, "count": 90, "is_parallel": true, "self": 68.80733094199718, "children": { "TorchPPOOptimizer.update": { "total": 117.34298860200317, "count": 4587, "is_parallel": true, "self": 117.34298860200317 } } } } } } } } }, "TrainerController._save_models": { "total": 0.134121038000103, "count": 1, "self": 0.0009038740001869883, "children": { "RLTrainer._checkpoint": { "total": 0.133217163999916, "count": 1, "self": 0.133217163999916 } } } } } } }