We propose a model-free reinforcement learning algorithm inspired by the popular randomized least squares value iteration (RLSVI) algorithm as well as the optimism principle. Unlike existing upper-confidence-bound (UCB) based approaches, which are often computationally intractable, our algorithm drives exploration by simply perturbing the training data with judiciously chosen i.i.d. scalar noises. To attain optimistic value function estimation without resorting to a UCB-style bonus, we introduce an optimistic reward sampling procedure. When the value functions can be represented by a function class $\mathcal{F}$, our algorithm achieves a worst-case regret bound of $\widetilde{O}(\mathrm{poly}(d_EH)\sqrt{T})$ where $T$ is the time elapsed, $H$ is the planning horizon and $d_E$ is the $\textit{eluder dimension}$ of $\mathcal{F}$. In the linear setting, our algorithm reduces to LSVI-PHE, a variant of RLSVI, that enjoys an $\widetilde{\mathcal{O}}(\sqrt{d^3H^3T})$ regret. We complement the theory with an empirical evaluation across known difficult exploration tasks.

提出了一种无模型强化学习算法，由于乐观原则和最小二乘价值迭代算法的启示，通过简单地使用谨慎选择的独立同分布的标量噪声扰乱训练数据来推动探索，在估计乐观值函数的同时引入了一种乐观的奖励采样过程，并证明了当数值函数可由函数类 \mathcal{F} 表示时，该算法实现了最坏情况下的遗憾度量边界，并在已知的难度探索任务上进行了实证评估。

使用通用价值函数逼近进行强化学习中的随机探索