BriefGPT.xyz
Feb, 2022
面向符号自动机编码目标的无模型强化学习
Model-Free Reinforcement Learning for Symbolic Automata-encoded Objectives
HTML
PDF
Anand Balakrishnan, Stefan Jaksic, Edgar Aguilar Lozano, Dejan Nickovic, Jyotirmoy Deshmukh
TL;DR
本文提出使用符号自动机的形式规范,来代替马尔可夫奖励,并定义了使用潜在奖励的策略,来提高强化学习的收敛性。
Abstract
reinforcement learning
(RL) is a popular approach for
robotic path planning
in uncertain environments. However, the control policies trained for an RL agent crucially depend on user-defined, state-based reward fu
→