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 2402.19212math.OCcs.LG
收藏

深度强化学习:一种凸优化方法

Deep Reinforcement Learning: A Convex Optimization Approach

Ather Gattami

AI总结:

针对连续状态动作空间的非线性系统强化学习问题,提出基于凸优化的回合式算法,通过求解最优Q函数的两层神经网络近似,证明算法收敛且参数可任意接近最优值,兼具收敛精度与速度优势。

摘要:

本文研究具有连续状态与动作空间的非线性系统的强化学习问题。我们提出一种回合式学习算法,在每个回合中,利用凸优化求解最优$Q$-函数的两层神经网络近似。该凸优化方法可保证,针对当前回合给定的采样状态和动作,每回合计算得到的权重均为最优。\n对于稳定非线性系统,我们证明该算法是收敛的,且训练后神经网络的收敛参数可任意接近最优神经网络参数。具体而言,若训练阶段的正则化参数为$ρ$,则训练后神经网络的参数收敛于$w$,其中$w$与最优参数$w^\star$的距离上界为$\mathcal{O}(ρ)$,即当回合数趋于无穷时,存在常数$C$使得$\\|w-w^\star\\| \le Cρ$。\n特别地,当正则化参数趋于零时,我们的算法可收敛到任意接近最优神经网络参数的结果。此外,由于凸优化算法具有多项式时间收敛性,该算法的收敛速度较快。

英文摘要:

In this paper, we consider reinforcement learning of nonlinear systems with continuous state and action spaces. We present an episodic learning algorithm, where we for each episode use convex optimization to find a two-layer neural network approximation of the optimal $Q$-function. The convex optimization approach guarantees that the weights calculated at each episode are optimal, with respect to the given sampled states and actions of the current episode. For stable nonlinear systems, we show that the algorithm converges and that the converging parameters of the trained neural network can be made arbitrarily close to the optimal neural network parameters. In particular, if the regularization parameter in the training phase is given by $ρ$, then the parameters of the trained neural network converge to $w$, where the distance between $w$ and the optimal parameters $w^\star$ is bounded by $\mathcal{O}(ρ)$. That is, when the number of episodes goes to infinity, there exists a constant $C$ such that \[ \|w-w^\star\| \le Cρ. \] In particular, our algorithm converges arbitrarily close to the optimal neural network parameters as the regularization parameter goes to zero. As a consequence, our algorithm converges fast due to the polynomial-time convergence of convex optimization algorithms.

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。

↑