神经符号RL中动作前置条件的三种注入策略
原标题：Managing Action Preconditions in Neuro-Symbolic RL: Three Placement Strategies for Embodied Agents
AI 摘要
该论文研究神经符号强化学习中动作前置条件的注入位置问题，将行为知识形式化为前置条件贝叶斯网络，并提出三种注入策略：推理时使用的符号验证器、训练和推理时均生效的符号执行器、以及将知识内化到网络中的符号学习器。在MiniGrid和Fetch两个基准上实验表明，三种策略均优于PPO+RND基线，符号执行器在解质量上领先；在Fetch上差异主要体现在样本效率，执行器和学习器约提前达到性能上限。该优势还推广到真实街道网络上的非具身路由任务，且验证器和执行器能保持行为可检查性。
正文节选
Neuro-Symbolic Embodied Intelligence Managing Action Preconditions in Neuro-Symbolic RL: Three Placement Strategies for Embodied Agents Abstract Humans carry behaviour knowledge of how to act in familiar situations into every new task rather than relearning it from scratch. There is no reason a Reinforcement Learning (RL) agent shouldn’t do the same: known behaviour patterns need not be learned, only applied. Neuro-symbolic RL bridges prior knowledge and RL by injecting symbolic knowledge alongs