Risk-Averse Reinforcement Learning via Dynamic Time-Consistent Risk Measures
원문 초록
Traditional reinforcement learning (RL) aims to maximize the expected total reward, while the risk of uncertain outcomes needs to be controlled to ensure reliable performance in a risk-averse setting. In this paper, we consider the problem of maximizing dynamic risk of a sequence of rewards in infinite-horizon Markov Decision Processes (MDPs). We adapt the Expected Conditional Risk Measures (ECRMs) to the infinite-horizon risk-averse MDP and prove its time consistency. Using a convex combination of expectation and conditional value-at-risk (CVaR) as a special one-step conditional risk measure, we reformulate the risk-averse MDP as a risk-neutral counterpart with augmented action space and manipulation on the immediate rewards. We further prove that the related Bellman operator is a contraction mapping, which guarantees the convergence of any value-based RL algorithms. Accordingly, we develop a risk-averse deep Q-learning framework, and our numerical studies based on two simple MDPs show that the risk-averse setting can reduce the variance and enhance robustness of the results.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Task Independent Capsule-Based Agents for Deep Q-Learning
Variation-resistant Q-learning: Controlling and Utilizing Estimation Bias in Reinforcement Learning for Better Performance
Robust Multi-Agent Reinforcement Learning with Model Uncertainty
Deep Reinforcement Learning Based Power Allocation for D2D Network
Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition
Investigating the Performance and Reliability, of the Q-Learning Algorithm in Various Unknown Environments
토론
이 논문과 연결된 포럼 글이 아직 없습니다.