Timezone: »

 
Poster
Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR
Kaiwen Wang · Nathan Kallus · Wen Sun

Thu Jul 27 04:30 PM -- 06:00 PM (PDT) @ Exhibit Hall 1 #326
in Poster Session 6 »
In this paper, we study risk-sensitive Reinforcement Learning (RL), focusing on the objective of Conditional Value at Risk (CVaR) with risk tolerance $\tau$. Starting with multi-arm bandits (MABs), we show the minimax CVaR regret rate is $\Omega(\sqrt{\tau^{-1}AK})$, where $A$ is the number of actions and $K$ is the number of episodes, and that it is achieved by an Upper Confidence Bound algorithm with a novel Bernstein bonus. For online RL in tabular Markov Decision Processes (MDPs), we show a minimax regret lower bound of $\Omega(\sqrt{\tau^{-1}SAK})$ (with normalized cumulative rewards), where $S$ is the number of states, and we propose a novel bonus-driven Value Iteration procedure. We show that our algorithm achieves the optimal regret of $\widetilde O(\sqrt{\tau^{-1}SAK})$ under a continuity assumption and in general attains a near-optimal regret of $\widetilde O(\tau^{-1}\sqrt{SAK})$, which is minimax-optimal for constant $\tau$. This improves on the best available bounds. By discretizing rewards appropriately, our algorithms are computationally efficient.
[ PDF]  [ Poster] 

Author Information

Kaiwen Wang (Cornell Tech)
Nathan Kallus (Cornell University)
Wen Sun (Cornell University)

More from the Same Authors