arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1811.03376cs.AI
收藏

多目标强化学习的元学习

Meta-Learning for Multi-objective Reinforcement Learning

KTH Royal Institute of Technology(瑞典皇家理工学院);Aalto University(阿尔托大学)

Xi Chen, Ali Ghadirzadeh, Mårten Björkman, Patric Jensfelt

摘要:

多目标强化学习(MORL)是标准强化学习(RL)方法的推广,用于解决由多个可能相互冲突的目标组成的顺序决策问题。通常,在这样的公式中,不存在同时优化所有目标的单个最优策略,而是必须找到多个策略,每个策略优化目标的偏好。换句话说,MORL是一个元学习问题,任务分布由偏好分布给出。我们证明,这样的配方结果在一个更好的近似的Pareto最优解的最优性和计算效率。我们评估了我们的方法,获得帕累托最优的政策,使用一些连续的控制问题,高自由度。

英文摘要:

Multi-objective reinforcement learning (MORL) is the generalization of standard reinforcement learning (RL) approaches to solve sequential decision making problems that consist of several, possibly conflicting, objectives. Generally, in such formulations, there is no single optimal policy which optimizes all the objectives simultaneously, and instead, a number of policies has to be found each optimizing a preference of the objectives. In other words, the MORL is framed as a meta-learning problem, with the task distribution given by a distribution over the preferences. We demonstrate that such a formulation results in a better approximation of the Pareto optimal solutions in terms of both the optimality and the computational efficiency. We evaluated our method on obtaining Pareto optimal policies using a number of continuous control problems with high degrees of freedom.

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。

↑