[PDF][PDF] Counterexample-Guided Policy Refinement in Multi-Agent Reinforcement Learning
B Gangopadhyay, P Dasgupta… - Proceedings of the 2023 …, 2023 - southampton.ac.uk
Single-agent Deep Reinforcement Learning (DRL) is a popular control technique where the
policy controlling agent learns to choose actions that maximize a discounted long-term …
policy controlling agent learns to choose actions that maximize a discounted long-term …
Safe Controller Synthesis for Nonlinear Systems Using Bayesian Optimization Enhanced Reinforcement Learning
C Jin, X Ma, T Ren, W Lin, Z Ding - Proceedings of the 27th ACM …, 2024 - dl.acm.org
Formal synthesis of safe controllers is essential for safety-critical cyber-physical systems. In
this paper, we propose a novel counterexample guided approach for synthesizing safe …
this paper, we propose a novel counterexample guided approach for synthesizing safe …