Zhi‐Quan Luo

Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent

2024 · arXiv (Cornell University)

We propose HyperAgent, a reinforcement learning (RL) algorithm based on the hypermodel framework for exploration in RL. HyperAgent allows for the efficient incremental approximation of posteriors associated with an optimal action-value function ($Q^\star$) without the …