State-free Reinforcement Learning
This work addresses the challenge of hyper-parameter tuning in RL for researchers and practitioners, representing an incremental step towards parameter-free RL.
The paper tackles the state-free reinforcement learning problem by designing an algorithm that operates without prior state information, achieving a regret bound independent of the full state space and dependent only on the reachable state set.
In this work, we study the \textit{state-free RL} problem, where the algorithm does not have the states information before interacting with the environment. Specifically, denote the reachable state set by ${S}^Π:= \{ s|\max_{π\in Π}q^{P, π}(s)>0 \}$, we design an algorithm which requires no information on the state space $S$ while having a regret that is completely independent of ${S}$ and only depend on ${S}^Π$. We view this as a concrete first step towards \textit{parameter-free RL}, with the goal of designing RL algorithms that require no hyper-parameter tuning.