arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.00691cs.ROcs.FLcs.LG
收藏

基于证伪的鲁棒对抗性强化学习

Falsification-Based Robust Adversarial Reinforcement Learning

Technische Universität München(慕尼黑工业大学)

Xiao Wang, Saasha Nair, Matthias Althoff

摘要:

强化学习(RL)在解决各种顺序决策问题方面取得了巨大进展,例如机器人中的控制任务。由于策略过度拟合训练环境,RL方法往往无法推广到安全关键的测试场景。鲁棒对抗强化学习(RARL)以前被提出来训练一个对抗网络,施加干扰到一个系统,这提高了测试场景中的鲁棒性。然而,基于神经网络的对手的一个问题是,在不手工制作复杂的奖励信号的情况下集成系统要求是困难的。安全证伪方法允许人们找到一组初始条件和一个输入序列,使得系统违反在时序逻辑中制定的给定属性。在本文中,我们提出了基于证伪的RARL(FRARL):这是第一个将时态逻辑证伪集成到对抗学习中以提高策略鲁棒性的通用框架。通过应用我们的证伪方法,我们不需要为对手构造额外的奖励函数。此外,我们评估我们的方法上的制动辅助系统和自适应巡航控制系统的自动驾驶汽车。我们的实验结果表明,与没有对手或对抗网络的训练相比,使用基于伪造的对手训练的策略更好地泛化,并且在测试场景中显示出更少的违反安全规范的行为。

英文摘要:

Reinforcement learning (RL) has achieved enormous progress in solving various sequential decision-making problems, such as control tasks in robotics. Since policies are overfitted to training environments, RL methods have often failed to be generalized to safety-critical test scenarios. Robust adversarial RL (RARL) was previously proposed to train an adversarial network that applies disturbances to a system, which improves the robustness in test scenarios. However, an issue of neural network-based adversaries is that integrating system requirements without handcrafting sophisticated reward signals are difficult. Safety falsification methods allow one to find a set of initial conditions and an input sequence, such that the system violates a given property formulated in temporal logic. In this paper, we propose falsification-based RARL (FRARL): this is the first generic framework for integrating temporal logic falsification in adversarial learning to improve policy robustness. By applying our falsification method, we do not need to construct an extra reward function for the adversary. Moreover, we evaluate our approach on a braking assistance system and an adaptive cruise control system of autonomous vehicles. Our experimental results demonstrate that policies trained with a falsification-based adversary generalize better and show less violation of the safety specification in test scenarios than those trained without an adversary or with an adversarial network.

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。

↑