论文标题
微筛子：深入增强学习的教学环境
MicroRacer: a didactic environment for Deep Reinforcement Learning
论文作者
论文摘要
Microcer是一个受赛车启发的简单开源环境，特别是用于深入强化学习的教学法。已经对环境的复杂性进行了明确的校准，以允许用户尝试许多不同的方法，网络和超参数设置，而无需复杂的软件或需要较长的培训时间。还提供用于主要学习算法的基线代理，例如DDPG，PPO，SAC，TD2和DSAC，以及在培训时间和性能方面的初步比较。
MicroRacer is a simple, open source environment inspired by car racing especially meant for the didactics of Deep Reinforcement Learning. The complexity of the environment has been explicitly calibrated to allow users to experiment with many different methods, networks and hyperparameters settings without requiring sophisticated software or the need of exceedingly long training times. Baseline agents for major learning algorithms such as DDPG, PPO, SAC, TD2 and DSAC are provided too, along with a preliminary comparison in terms of training time and performance.
