基于Atari-2600基准的基于宽度的Lookaheads与学习基础策略和启发式
Width-based Lookaheads with Learnt Base Policies and Heuristics Over the Atari-2600 Benchmark
摘要:
我们提出了新的宽度为基础的规划和学习算法的灵感来自仔细分析以前的宽度为基础的规划师的设计决策。这些算法应用于Atari-2600游戏,我们的最佳性能算法,新颖性引导关键路线学习(N-CPL),优于以前介绍的基于宽度的规划和学习算法$π$ -IW(1),$π$ -IW(1)+和$π$ -HIW(n,1)。此外,我们提出了一个分类的Atari-2600游戏,根据他们的一些定义特征。对游戏的这种分析提供了对所引入算法的行为和性能的进一步了解。也就是说,对于具有大分支因子的游戏和具有稀疏有意义奖励的游戏,N-CPL优于$π$ -IW、$π$ -IW(1)+和$π$ -HIW(n,1)。
英文摘要:
We propose new width-based planning and learning algorithms inspired from a careful analysis of the design decisions made by previous width-based planners. The algorithms are applied over the Atari-2600 games and our best performing algorithm, Novelty guided Critical Path Learning (N-CPL), outperforms the previously introduced width-based planning and learning algorithms $π$-IW(1), $π$-IW(1)+ and $π$-HIW(n, 1). Furthermore, we present a taxonomy of the Atari-2600 games according to some of their defining characteristics. This analysis of the games provides further insight into the behaviour and performance of the algorithms introduced. Namely, for games with large branching factors, and games with sparse meaningful rewards, N-CPL outperforms $π$-IW, $π$-IW(1)+ and $π$-HIW(n, 1).
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。