arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.06545cs.LG
收藏

可证明有效的因果基于模型的强化学习

Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization

Politecnico di Milano(米兰理工大学);ETH Zurich(苏黎世联邦理工学院);Imperial College London(伦敦帝国理工学院);Twitter(推特公司);University of Oxford(牛津大学)

Mirco Mutti, Riccardo De Santi, Emanuele Rossi, Juan Felipe Calderon, Michael Bronstein, Marcello Restelli

摘要:

在顺序决策设置中,代理的目标是在一个大的,可能是无限的环境集上实现系统的泛化。这种环境被建模为离散马尔可夫决策过程的状态和动作表示通过一个特征向量。环境的基本结构允许将过渡动态因素分解为两个部分:一个是特定于环境的,另一个是共享的。考虑一组共享运动定律的环境作为示例。在这种情况下,代理可以从这些环境的子集中获取有限数量的无奖励交互。然后,智能体必须能够近似地解决在原始集合中的任何环境上定义的任何规划任务,仅依赖于上述交互。我们能否设计出一种可证明有效的算法来实现系统化推广这一雄心勃勃的目标?本文对此问题给出了部分肯定的回答。首先,我们提供了一个易于处理的系统推广的制定采用因果的观点。然后,在特定的结构假设下,我们提供了一个简单的学习算法,保证任何所需的规划误差到一个不可避免的次优项,同时展示一个多项式样本的复杂性。

英文摘要:

In the sequential decision making setting, an agent aims to achieve systematic generalization over a large, possibly infinite, set of environments. Such environments are modeled as discrete Markov decision processes with both states and actions represented through a feature vector. The underlying structure of the environments allows the transition dynamics to be factored into two components: one that is environment-specific and another that is shared. Consider a set of environments that share the laws of motion as an example. In this setting, the agent can take a finite amount of reward-free interactions from a subset of these environments. The agent then must be able to approximately solve any planning task defined over any environment in the original set, relying on the above interactions only. Can we design a provably efficient algorithm that achieves this ambitious goal of systematic generalization? In this paper, we give a partially positive answer to this question. First, we provide a tractable formulation of systematic generalization by employing a causal viewpoint. Then, under specific structural assumptions, we provide a simple learning algorithm that guarantees any desired planning error up to an unavoidable sub-optimality term, while showcasing a polynomial sample complexity.

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。

↑