论文标题
Wang-Foster-Kakade的变体用于折扣设置
A Variant of the Wang-Foster-Kakade Lower Bound for the Discounted Setting
论文作者
论文摘要
最近，Wang等人。 （2020年）在有限的 - 摩尼子案例中具有线性可实现的值函数和良好的特征覆盖率，显示出高度有趣的硬度结果。在本说明中，我们表明，一旦适应了折扣设置，就可以将构造简化为具有一维功能的2态MDP，因此即使使用无限的数据也无法学习。
Recently, Wang et al. (2020) showed a highly intriguing hardness result for batch reinforcement learning (RL) with linearly realizable value function and good feature coverage in the finite-horizon case. In this note we show that once adapted to the discounted setting, the construction can be simplified to a 2-state MDP with 1-dimensional features, such that learning is impossible even with an infinite amount of data.
