arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.08732cs.LGcs.AI
收藏

线性迁移模型下的元学习MDP

Meta Learning MDPs with Linear Transition Models

Technical University of Munich(慕尼黑工业大学);Microsoft Research, NYC(微软研究院纽约)

Robert Müller, Aldo Pacchiano

摘要:

我们研究了马尔可夫决策过程(MDP)中的元学习,在未贴现的情节设置中具有线性转移模型。在基于模型接近度的任务共享性度量下,我们研究了由偏置项和方差分量指定的模型分布的任务族。然后,我们提出了BUC-MatrixRL,这是UC-Matrix RL算法的一个版本,并表明它可以有意义地利用一组采样的训练任务,通过学习任务分布的偏差参数的估计量来快速解决从相同任务分布中采样的测试任务。该分析利用并扩展了学习线性回归和线性强盗设置的学习结果,以更一般的情况下,MDP的线性过渡模型。我们证明了,相比于孤立地学习任务,BUC-Matrix RL在高偏差低方差任务分布的转移遗憾方面提供了显着的改善。

英文摘要:

We study meta-learning in Markov Decision Processes (MDP) with linear transition models in the undiscounted episodic setting. Under a task sharedness metric based on model proximity we study task families characterized by a distribution over models specified by a bias term and a variance component. We then propose BUC-MatrixRL, a version of the UC-Matrix RL algorithm, and show it can meaningfully leverage a set of sampled training tasks to quickly solve a test task sampled from the same task distribution by learning an estimator of the bias parameter of the task distribution. The analysis leverages and extends results in the learning to learn linear regression and linear bandit setting to the more general case of MDP's with linear transition models. We prove that compared to learning the tasks in isolation, BUC-Matrix RL provides significant improvements in the transfer regret for high bias low variance task distributions.

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。

↑