arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.01577cs.LGcs.AI
收藏

约束马尔可夫决策过程的一个可证有效的无模型算法

A Provably-Efficient Model-Free Algorithm for Constrained Markov Decision Processes

University of Michigan, Ann Arbor(密歇根大学安娜堡分校)

Honghao Wei, Xin Liu, Lei Ying

摘要:

针对具有次线性后悔和零约束违反的约束马尔可夫决策过程,提出了第一个无模型、无仿真器的强化学习算法。该算法被命名为Triple-Q,因为它包括三个关键组件:用于累积奖励的Q函数(也称为动作-价值函数)、用于约束累积效用的Q函数以及(过度)估计累积约束违规的虚拟队列。在Triple-Q下,在每一步中,基于伪Q值选择动作,伪Q值是三个“Q”值的组合。该算法更新的回报和效用Q值与学习率取决于访问计数到相应的(状态,动作)对,并定期重置。在情节CMDP设置中,Triple-Q实现$\tilde{\cal O}\left(\frac{1 }δH^4 S^{\frac{1}{2}}A^{\frac{1}{2}}K^{\frac{4}{5}} \right)$后悔,其中$K$是情节的总数,$H$是每个情节中的步数,$S$是状态的数量,$A$是动作的数量,$δ$是斯莱特常数。此外,当$K$足够大时,Triple-Q保证零约束违反,无论是在期望上还是以高概率。最后,三重Q的计算复杂性类似于无约束MDP的SARSA,并且是计算高效的。

英文摘要:

This paper presents the first model-free, simulator-free reinforcement learning algorithm for Constrained Markov Decision Processes (CMDPs) with sublinear regret and zero constraint violation. The algorithm is named Triple-Q because it includes three key components: a Q-function (also called action-value function) for the cumulative reward, a Q-function for the cumulative utility for the constraint, and a virtual-Queue that (over)-estimates the cumulative constraint violation. Under Triple-Q, at each step, an action is chosen based on the pseudo-Q-value that is a combination of the three "Q" values. The algorithm updates the reward and utility Q-values with learning rates that depend on the visit counts to the corresponding (state, action) pairs and are periodically reset. In the episodic CMDP setting, Triple-Q achieves $\tilde{\cal O}\left(\frac{1 }δH^4 S^{\frac{1}{2}}A^{\frac{1}{2}}K^{\frac{4}{5}} \right)$ regret, where $K$ is the total number of episodes, $H$ is the number of steps in each episode, $S$ is the number of states, $A$ is the number of actions, and $δ$ is Slater's constant. Furthermore, Triple-Q guarantees zero constraint violation, both on expectation and with a high probability, when $K$ is sufficiently large. Finally, the computational complexity of Triple-Q is similar to SARSA for unconstrained MDPs and is computationally efficient.

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。

↑