具有逻辑指导的认证强化学习
Certified Reinforcement Learning with Logic Guidance
AI总结：
针对安全关键控制问题，提出一种无模型RL算法，利用LTL目标和LDGBA实时塑造奖励，并在假设下保证最大概率满足规范。
摘要：
强化学习（RL）是一种被广泛采用的机器学习架构，已应用于多种控制问题。然而，在安全关键领域中的应用需要一种系统化、形式化的方法，将需求指定为任务或目标。我们提出一种无模型RL算法，使得能够使用线性时序逻辑（LTL）为未知的连续状态/动作马尔可夫决策过程（MDP）表述目标。给定的LTL属性被转换为极限确定性广义Büchi自动机（LDGBA），随后用于即时塑造同步奖励函数。在特定假设下，该算法保证能够综合出一种控制策略，其轨迹以最大概率满足LTL规范。
英文摘要：
Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of control problems. However, applications in safety-critical domains require a systematic and formal approach to specifying requirements as tasks or goals. We propose a model-free RL algorithm that enables the use of Linear Temporal Logic (LTL) to formulate a goal for unknown continuous-state/action Markov Decision Processes (MDPs). The given LTL property is translated into a Limit-Deterministic Generalised Buchi Automaton (LDGBA), which is then used to shape a synchronous reward function on-the-fly. Under certain assumptions, the algorithm is guaranteed to synthesise a control policy whose traces satisfy the LTL specification with maximal probability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
