arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2108.05533cs.LGmath.OCstat.ML
收藏

线性函数逼近的有效局部规划

Efficient Local Planning with Linear Function Approximation

DeepMind(深度思维);University of Alberta(阿尔伯塔大学)

Dong Yin, Botao Hao, Yasin Abbasi-Yadkori, Nevena Lazić, Csaba Szepesvári

摘要:

我们研究查询和计算效率的规划算法与线性函数近似和模拟器。我们假设代理只能本地访问模拟器,这意味着代理只能在以前访问过的状态下查询模拟器。这种设置比许多先前的具有生成模型的强化学习的工作更实用。我们提出了两个算法,命名为置信蒙特卡罗最小二乘政策迭代(置信MC-LSPI)和置信蒙特卡罗Politex(置信MC-Politex)的这种设置。假设所有策略的Q函数在状态-动作对的已知特征中是线性的,我们证明了我们的算法在特征的维度、有效规划范围和目标次优性上具有多项式查询和计算成本,而这些成本与状态空间的大小无关。我们的工作的一个技术贡献是引入了一种新的证明技术,利用虚拟策略迭代算法。我们使用这种方法来利用现有的结果$\ell_\infty$有界的近似策略迭代表明,我们的算法可以学习的最优策略,即使只有本地访问的模拟器给定的初始状态。我们相信,这种技术可以扩展到更广泛的设置超出了这项工作。

英文摘要:

We study query and computationally efficient planning algorithms with linear function approximation and a simulator. We assume that the agent only has local access to the simulator, meaning that the agent can only query the simulator at states that have been visited before. This setting is more practical than many prior works on reinforcement learning with a generative model. We propose two algorithms, named confident Monte Carlo least square policy iteration (Confident MC-LSPI) and confident Monte Carlo Politex (Confident MC-Politex) for this setting. Under the assumption that the Q-functions of all policies are linear in known features of the state-action pairs, we show that our algorithms have polynomial query and computational costs in the dimension of the features, the effective planning horizon, and the targeted sub-optimality, while these costs are independent of the size of the state space. One technical contribution of our work is the introduction of a novel proof technique that makes use of a virtual policy iteration algorithm. We use this method to leverage existing results on $\ell_\infty$-bounded approximate policy iteration to show that our algorithm can learn the optimal policy for the given initial state even only with local access to the simulator. We believe that this technique can be extended to broader settings beyond this work.

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。

↑