arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.03078cs.LGcs.AI
收藏

基于非参数值近似的像素快速高效强化学习

Fast and Data Efficient Reinforcement Learning from Pixels via Non-Parametric Value Approximation

University of New South Wales(新南威尔士大学);University of Amsterdam(阿姆斯特丹大学)

Alexander Long, Alan Blair, Herke van Hoof

摘要:

我们提出了非参数近似的轨迹间返回(NAIT),一个强化学习算法的离散动作,基于像素的环境,是高度的样本和计算效率。NAIT是一种惰性学习方法,其更新相当于情节完成时的情节蒙特卡洛,但它允许在情节正在进行时稳定地纳入奖励。我们使用一个固定的域不可知表示,简单的基于距离的探索和基于邻近图的查找,以促进非常快的执行。我们在ATARI 100k的26和57游戏变体上对NAIT进行了经验评估,尽管它很简单,但它在在线设置中实现了具有竞争力的性能,在墙时间内加速超过100倍。

英文摘要:

We present Nonparametric Approximation of Inter-Trace returns (NAIT), a Reinforcement Learning algorithm for discrete action, pixel-based environments that is both highly sample and computation efficient. NAIT is a lazy-learning approach with an update that is equivalent to episodic Monte-Carlo on episode completion, but that allows the stable incorporation of rewards while an episode is ongoing. We make use of a fixed domain-agnostic representation, simple distance based exploration and a proximity graph-based lookup to facilitate extremely fast execution. We empirically evaluate NAIT on both the 26 and 57 game variants of ATARI100k where, despite its simplicity, it achieves competitive performance in the online setting with greater than 100x speedup in wall-time.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑