Sample-Optimal Zero-Violation Safety For Continuous Control
원문 초록
In this paper, we study the problem of ensuring safety with a few shots of samples for partially unknown systems. We first characterize a fundamental limit when producing safe actions is not possible due to insufficient information or samples. Then, we develop a technique that can generate provably safe actions and recovery behaviors using a minimum number of samples. In the performance analysis, we also establish Nagumos theorem - like results with relaxed assumptions, which is potentially useful in other contexts. Finally, we discuss how the proposed method can be integrated into a policy gradient algorithm to assure safety and stability with a handful of samples without stabilizing initial policies or generative models to probe safe actions.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty
Improving Value Estimation Critically Enhances Vanilla Policy Gradient
RLBenchNet: The Right Network for the Right Reinforcement Learning Task
Guided Policy Optimization under Partial Observability
Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.