Global Policy Construction in Modular Reinforcement Learning
نویسندگان
چکیده
We propose a modular reinforcement learning algorithm which decomposes a Markov decision process into independent modules. Each module is trained using Sarsa(λ). We introduce three algorithms for forming global policy from modules policies, and demonstrate our results using a 2D grid world.
منابع مشابه
On Scalability Issues in Reinforcement Learning for Self-Reconfiguring Modular Robots
Self-reconfiguring modular robots have been receiving great attention because advances in our field are expected to deliver ultra-adaptable and robust systems. There has been remarkable progress in modular hardware and distributed controllers, e.g., [1]–[4], some of which were designed automatically by genetic algorithms, e.g., [1]. But how can the greatest adaptability be achieved? Our positio...
متن کاملOptimizing Tutorial Planning in Educational Games: A Modular Reinforcement Learning Approach
Recent years have seen a growing interest in educational games, which integrate the engaging features of digital games with the personalized learning functionalities of intelligent tutoring systems. A key challenge in creating educational games, particularly those supported with interactive narrative, is devising narrativecentered tutorial planners, which dynamically adapt gameplay events to in...
متن کاملDistributed reinforcement learning for self-reconfiguring modular robots
In this thesis, we study distributed reinforcement learning in the context of automating the design of decentralized control for groups of cooperating, coupled robots. Specifically, we develop a framework and algorithms for automatically generating distributed controllers for self-reconfiguring modular robots using reinforcement learning. The promise of self-reconfiguring modular robots is that...
متن کاملAutomated Design of Adaptive Controllers for Modular Robots using Reinforcement Learning
Designing distributed controllers for self-reconfiguring modular robots has been consistently challenging. We have developed a reinforcement learning approach which can be used both to automate controller design and to adapt robot behavior on-line. In this paper, we report on our study of reinforcement learning in the domain of self-reconfigurable modular robots: the underlying assumptions, the...
متن کاملMultiple-Goal Reinforcement Learning with Modular Sarsa(O)
We present a new algorithm, GM-Sarsa(O), for finding approximate solutions to multiple-goal reinforcement learning problems that are modeled as composite Markov decision processes. According to our formulation different sub-goals are modeled as MDPs that are coupled by the requirement that they share actions. Existing reinforcement learning algorithms address similar problem formulations by fir...
متن کامل