arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.04864cs.LG
收藏

增强贝叶斯策略搜索

Augmented Bayesian Policy Search

University of Würzburg(维尔茨堡大学);Univ. Lille(里尔大学);Inria(法国国家信息与自动化研究所);CNRS(法国国家科学研究中心);Centrale Lille(里尔中央理工学院);TU Darmstadt(达姆施塔特工业大学);Hessian Center for Artificial Intelligence (Hessian.ai)(黑森人工智能中心)

Mahdi Kallel, Debabrota Basu, Riad Akrour, Carlo D'Eramo

AI总结:

本文提出增强贝叶斯搜索(ABS),利用性能差异引理将动作价值函数引入贝叶斯优化均值函数,融合确定性策略梯度,在高维运动任务中取得有竞争力的表现。

摘要:

在物理系统上实现时,确定性策略通常比随机策略更受青睐。它们可以防止不稳定和有害的行为,同时更易于实现和解释。然而,在实践中,探索主要由随机策略执行。一阶贝叶斯优化(BO)方法提供了一种使用确定性策略进行探索的原则性方法。这是通过目标函数及其梯度的学习概率模型来实现的。尽管如此,此类方法将策略搜索视为黑盒问题,因此忽略了问题的强化学习本质。在这项工作中,我们利用性能差异引理为概率模型引入了一种新的均值函数。这导致用动作价值函数增强BO方法。因此,我们将我们的方法称为增强贝叶斯搜索(ABS)。有趣的是,这种新的均值函数用确定性策略梯度增强了后验梯度,有效地弥合了BO与策略梯度方法之间的差距。所得算法结合了直接策略搜索的便利性与强化学习的可扩展性。我们在高维运动问题上验证了ABS,并展示了与现有直接策略搜索方案相比具有竞争力的性能。

英文摘要:

Deterministic policies are often preferred over stochastic ones when implemented on physical systems. They can prevent erratic and harmful behaviors while being easier to implement and interpret. However, in practice, exploration is largely performed by stochastic policies. First-order Bayesian Optimization (BO) methods offer a principled way of performing exploration using deterministic policies. This is done through a learned probabilistic model of the objective function and its gradient. Nonetheless, such approaches treat policy search as a black-box problem, and thus, neglect the reinforcement learning nature of the problem. In this work, we leverage the performance difference lemma to introduce a novel mean function for the probabilistic model. This results in augmenting BO methods with the action-value function. Hence, we call our method Augmented Bayesian Search~(ABS). Interestingly, this new mean function enhances the posterior gradient with the deterministic policy gradient, effectively bridging the gap between BO and policy gradient methods. The resulting algorithm combines the convenience of the direct policy search with the scalability of reinforcement learning. We validate ABS on high-dimensional locomotion problems and demonstrate competitive performance compared to existing direct policy search schemes.

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。

↑