时间抽象是分层强化学习中的重要研究方向,而子目标是时间抽象形成的核心元素.目前,大部分分层强化学习需要人工给出子目标或设定子目标数量.然而,在很多情况下,这不仅需要大量的人工干预,而且所作设定未必适合对应场景,在动态环境未知...时间抽象是分层强化学习中的重要研究方向,而子目标是时间抽象形成的核心元素.目前,大部分分层强化学习需要人工给出子目标或设定子目标数量.然而,在很多情况下,这不仅需要大量的人工干预,而且所作设定未必适合对应场景,在动态环境未知的指导下,这一问题尤为突出.针对此,提出基于优化子目标数的Option-Critic算法(Option-Critic algorithm based on Sub-goal Quantity Optimization,OC-SQO),增加了智能体对环境的探索部分,通过与环境的简单交互,得到适用于应用场景的初始子目标数量估值,并在此基础上识别子目标,然后利用通过策略梯度生成对应的抽象,使用初态、内部策略和终止函数构成的三元组表示,以此进行训练,根据交互得到的抽象改变当前状态,不断迭代优化.OC-SQO算法可以在任意状态下开始执行,不要求预先指定子目标和参数,在执行过程中使用策略梯度生成内部策略、抽象间策略和终止函数,不需要提供内部奖赏信号,也无需获取子目标的情况,尽可能地减少了人工干预.实验验证了算法的有效性.展开更多
文章分析了M A S建模方法学提出的动因,指出了M A S建模中的关键问题;阐述了基于A gen t的建模方法学分析阶段的过程及其不足,研究了对系统子目标进行表述、求解的规范化工具——G/A矩阵及其求解方法;并在此基础上提出了一种新的M A S...文章分析了M A S建模方法学提出的动因,指出了M A S建模中的关键问题;阐述了基于A gen t的建模方法学分析阶段的过程及其不足,研究了对系统子目标进行表述、求解的规范化工具——G/A矩阵及其求解方法;并在此基础上提出了一种新的M A S中个体A gen t的识别方法,最后通过实例说明该方法简单易行。展开更多
In reinforcement learning an agent may explore ineffectively when dealing with sparse reward tasks where finding a reward point is difficult.To solve the problem,we propose an algorithm called hierarchical deep reinfo...In reinforcement learning an agent may explore ineffectively when dealing with sparse reward tasks where finding a reward point is difficult.To solve the problem,we propose an algorithm called hierarchical deep reinforcement learning with automatic sub-goal identification via computer vision(HADS)which takes advantage of hierarchical reinforcement learning to alleviate the sparse reward problem and improve efficiency of exploration by utilizing a sub-goal mechanism.HADS uses a computer vision method to identify sub-goals automatically for hierarchical deep reinforcement learning.Due to the fact that not all sub-goal points are reachable,a mechanism is proposed to remove unreachable sub-goal points so as to further improve the performance of the algorithm.HADS involves contour recognition to identify sub-goals from the state image where some salient states in the state image may be recognized as sub-goals,while those that are not will be removed based on prior knowledge.Our experiments verified the effect of the algorithm.展开更多
文摘时间抽象是分层强化学习中的重要研究方向,而子目标是时间抽象形成的核心元素.目前,大部分分层强化学习需要人工给出子目标或设定子目标数量.然而,在很多情况下,这不仅需要大量的人工干预,而且所作设定未必适合对应场景,在动态环境未知的指导下,这一问题尤为突出.针对此,提出基于优化子目标数的Option-Critic算法(Option-Critic algorithm based on Sub-goal Quantity Optimization,OC-SQO),增加了智能体对环境的探索部分,通过与环境的简单交互,得到适用于应用场景的初始子目标数量估值,并在此基础上识别子目标,然后利用通过策略梯度生成对应的抽象,使用初态、内部策略和终止函数构成的三元组表示,以此进行训练,根据交互得到的抽象改变当前状态,不断迭代优化.OC-SQO算法可以在任意状态下开始执行,不要求预先指定子目标和参数,在执行过程中使用策略梯度生成内部策略、抽象间策略和终止函数,不需要提供内部奖赏信号,也无需获取子目标的情况,尽可能地减少了人工干预.实验验证了算法的有效性.
文摘文章分析了M A S建模方法学提出的动因,指出了M A S建模中的关键问题;阐述了基于A gen t的建模方法学分析阶段的过程及其不足,研究了对系统子目标进行表述、求解的规范化工具——G/A矩阵及其求解方法;并在此基础上提出了一种新的M A S中个体A gen t的识别方法,最后通过实例说明该方法简单易行。
基金supported by the National Natural Science Foundation of China(61303108)Suzhou Key Industries Technological Innovation-Prospective Applied Research Project(SYG201804)+2 种基金A Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)the Fundamental Research Funds for the Gentral UniversitiesJLU(93K172020K25)。
文摘In reinforcement learning an agent may explore ineffectively when dealing with sparse reward tasks where finding a reward point is difficult.To solve the problem,we propose an algorithm called hierarchical deep reinforcement learning with automatic sub-goal identification via computer vision(HADS)which takes advantage of hierarchical reinforcement learning to alleviate the sparse reward problem and improve efficiency of exploration by utilizing a sub-goal mechanism.HADS uses a computer vision method to identify sub-goals automatically for hierarchical deep reinforcement learning.Due to the fact that not all sub-goal points are reachable,a mechanism is proposed to remove unreachable sub-goal points so as to further improve the performance of the algorithm.HADS involves contour recognition to identify sub-goals from the state image where some salient states in the state image may be recognized as sub-goals,while those that are not will be removed based on prior knowledge.Our experiments verified the effect of the algorithm.
