ILCL：从带时间约束的示范中逆向学习逻辑约束
ILCL: Inverse Logic-Constraint Learning from Temporally Constrained Demonstrations
AI总结：
本文提出逆向逻辑约束学习（ILCL），将时间约束学习建模为遗传算法时序逻辑挖掘与逻辑约束强化学习的零和博弈，在多个任务上优于现有方法并实现真实世界迁移。
摘要：
我们旨在解决从示范中学习时间约束的问题，以复现类似示范的逻辑约束行为。由于可能规约的组合空间巨大以及非马尔可夫约束的不适定性质，学习逻辑约束具有挑战性。为解决这一问题，我们提出了一种新颖的时间约束学习方法，称为逆向逻辑约束学习（ILCL）。我们的方法将逆向约束学习（ICL）构建为一个双人零和博弈，博弈双方分别是：1）基于遗传算法的时间逻辑挖掘（GA-TL-Mining）和2）逻辑约束强化学习（Logic-CRL）。GA-TL-Mining在无需预定义模板的情况下，高效构建参数化截断线性时序逻辑（TLTL）的语法树。随后，Logic-CRL通过一种新颖的约束重分配方案，在构建的TLTL约束下寻找最大化任务奖励的策略。我们的评估表明，在四个带时间约束的任务上，ILCL在学习与迁移TL约束方面优于最先进的基线方法。我们还展示了向真实世界浅孔插销任务的成功迁移。
英文摘要：
We aim to solve the problem of temporal-constraint learning from demonstrations to reproduce demonstration-like logic-constrained behaviors. Learning logic constraints is challenging due to the combinatorially large space of possible specifications and the ill-posed nature of non-Markovian constraints. To figure it out, we introduce a novel temporal-constraint learning method, which we call inverse logic-constraint learning (ILCL). Our method frames ICL as a two-player zero-sum game between 1) a genetic algorithm-based temporal-logic mining (GA-TL-Mining) and 2) logic-constrained reinforcement learning (Logic-CRL). GA-TL-Mining efficiently constructs syntax trees for parameterized truncated linear temporal logic (TLTL) without predefined templates. Subsequently, Logic-CRL finds a policy that maximizes task rewards under the constructed TLTL constraints via a novel constraint redistribution scheme. Our evaluations show ILCL outperforms state-of-the-art baselines in learning and transferring TL constraints on four temporally constrained tasks. We also demonstrate successful transfer to real-world peg-in-shallow-hole tasks.
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。
