paper-with-me

Papers

Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees

2024-05-29 · Dohyeong Kim, Taehyun Cho, Seungyub Han, Hojun Chung, Kyungjae Lee, Songhwai Oh

The field of risk-constrained reinforcement learning (RCRL) has been developed to effectively reduce the likelihood of worst-case scenarios by explicitly handling risk-measure-based constraints. However, the nonlinearity of risk measures makes it challenging to achieve convergence and optimality. To overcome the difficulties posed by the nonlinearity, we propose a spectral risk measure-constrained RL algorithm, spectral-risk-constrained policy optimization (SRCPO), a bilevel optimization approach that utilizes the duality of spectral risk measures. In the bilevel optimization structure, the outer problem involves optimizing dual variables derived from the risk measures, while the inner problem involves finding an optimal policy given these dual variables. The proposed method, to the best of our knowledge, is the first to guarantee convergence to an optimum in the tabular setting. Furthermore, the proposed method has been evaluated on continuous control tasks and showed the best performance among other RCRL algorithms satisfying the constraints.

📄 PDF Abstract BibTeX arXiv:2405.18698

Code (0)

등록된 구현이 없습니다.

Tasks

Bilevel Optimizationcontinuous-controlContinuous Controlreinforcement-learningReinforcement LearningSafe Reinforcement Learning

Similar Papers 제목 키워드 기반

SOREL: A Stochastic Algorithm for Spectral Risks Minimization

2024-07-19 · Yuze Ge, Rujun Jiang

The spectral risk has wide applications in machine learning, especially in real-world decision-making, where people are not only concerned with models' average performance. By assigning different weights to the losses of…

Decision Making

Risk-sensitive Actor-Critic with Static Spectral Risk Measures for Online and Offline Reinforcement Learning

2025-07-05 · Mehrdad Moghimi, Hyejin Ku arxiv

The development of Distributional Reinforcement Learning (DRL) has introduced a natural way to incorporate risk sensitivity into value-based and actor-critic methods by employing risk measures other than expectation in t…

Reinforcement LearningOffline RL

Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning

2025-01-03 · Mehrdad Moghimi, Hyejin Ku

In domains such as finance, healthcare, and robotics, managing worst-case scenarios is critical, as failure to do so can lead to catastrophic outcomes. Distributional Reinforcement Learning (DRL) provides a natural frame…

Decision MakingDistributional Reinforcement Learning

Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems

2024-03-06 · Wesley A. Suttle, Vipul K. Sharma, Krishna C. Kosaraju, S. Sivaranjani 외

We develop provably safe and convergent reinforcement learning (RL) algorithms for control of nonlinear dynamical systems, bridging the gap between the hard safety guarantees of control theory and the convergence guarant…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement Learning

Supervised Learning with General Risk Functionals

2022-06-27 · Liu Leqi, Audrey Huang, Zachary C. Lipton, Kamyar Azizzadenesheli

Standard uniform convergence results bound the generalization gap of the expected loss over a hypothesis class. The emergence of risk-sensitive learning requires generalization guarantees for functionals of the loss dist…