On the Global Convergence of Risk-Averse Policy Gradient Methods with Expected Conditional Risk Measures
–arXiv.org Artificial Intelligence
Risk-sensitive reinforcement learning (RL) has become a popular tool to control the risk of uncertain outcomes and ensure reliable performance in various sequential decision-making problems. While policy gradient methods have been developed for risk-sensitive RL, it remains unclear if these methods enjoy the same global convergence guarantees as in the risk-neutral case. In this paper, we consider a class of dynamic time-consistent risk measures, called Expected Conditional Risk Measures (ECRMs), and derive policy gradient updates for ECRM-based objective functions. Under both constrained direct parameterization and unconstrained softmax parameterization, we provide global convergence and iteration complexities of the corresponding risk-averse policy gradient algorithms. We further test risk-averse variants of REINFORCE and actor-critic algorithms to demonstrate the efficacy of our method and the importance of risk control.
arXiv.org Artificial Intelligence
May-29-2023
- Country:
- Europe > Russia (0.04)
- Asia > Russia (0.04)
- North America > United States
- Ohio > Franklin County
- Columbus (0.04)
- Michigan > Washtenaw County
- Ann Arbor (0.14)
- Ohio > Franklin County
- Genre:
- Research Report (0.50)
- Technology: