AI 中文总结
研究如何在强化学习中进行信息探索，提出基于贝叶斯核方法理论的随机特征信息增益（RFIG），用随机傅里叶特征近似信息增益，给出误差界并避免黑箱问题，实践细节使其可扩展到深度RL场景，实验显示其性能有竞争力且理论解释优。
AI 中文摘要
表示学习已将经典探索策略扩展到深度强化学习，但常使算法更复杂且理论保证更难建立。我们引入基于贝叶斯核方法理论的随机特征信息增益（RFIG），用随机傅里叶特征近似信息增益并在不可数空间计算探索奖励。给出信息增益近似的误差界，避免基于神经网络的不确定性估计的黑箱问题。还给出使RFIG可扩展到深度强化学习场景的实践细节。实验评估表明RFIG性能有竞争力且理论解释更优。
英文摘要
Representation learning has enabled classical exploration strategies to be extended to deep Reinforcement Learning (RL), but often makes algorithms more complex and theoretical guarantees harder to establish. We introduce Random Feature Information Gain (RFIG), grounded in Bayesian kernel methods theory, which uses random Fourier features to approximate information gain and compute exploration bonuses in non-countable spaces. We provide error bounds on information gain approximation and avoid the black-box aspects of neural network-based uncertainty estimation, for optimism-based exploration. We present practical details that make RFIG scalable to deep RL scenarios, enabling smooth integration into standard deep RL algorithms. Experimental evaluation across diverse control and navigation tasks demonstrates that RFIG achieves competitive performance with well-established deep exploration methods while offering superior theoretical interpretation.
