Competitive Reinforcement Learning for Combinatorial Problems
نویسندگان
چکیده
This paper shows that the competitive learning rule found in Learning Vector Quantization (LVQ) serves as a promising function approximator to enable reinforcement learning methods to cope with a large decision search space, defined in terms of different classes of input patterns, like those found in the game of Go. In particular, this paper describes S[arsa]LVQ, a novel reinforcement learning algorithm and shows its feasibility for Go. As the distributed LVQ representation corresponds to a (quantized) codebook of compressed and generalized pattern templates, the state space requirements for online reinforcement methods are significantly reduced, thus decreasing the complexity of the decision space and consequently improving the play performance. As a result of competitive learning, SLVQ can win against heuristic players and starts to level off against stronger opponents such as Wally. SLVQ outperforms S[arsa]Linear when playing against both a heuristic player and Wally. Furthermore, while playing Go, SLVQ learns to stay alive while SLinear fails to do so.
منابع مشابه
Global Search in Combinatorial Optimization using Reinforcement Learning Algorithms
This paper presents two approaches that address the problems of the local character of the search and imprecise state representation of reinforcement learning (RL) algorithms for solving combinatorial optimization problems. The first, Bayesian, approach aims to capture solution parameter interdependencies. The second approach combines local information as encoded by typical RL schemes and globa...
متن کاملAn Approach to Solving Combinatorial Optimization Problems Using a Population of Reinforcement Learning Agents
This paper presents an approach that uses reinforcement learning (RL) algorithms to solve combinatorial optimization problems. In particular, the approach combines both local and global search characteristics: local information as encoded by typical RL schemes and global information as contained in a population of search agents. The effectiveness of the approach is demonstrated on both the Asym...
متن کاملReinforcement learning based local search for grouping problems: A case study on graph coloring
Grouping problems aim to partition a set of items into multiple mutually disjoint subsets according to some specific criterion and constraints. Grouping problems cover a large class of important combinatorial optimization problems that are generally computationally difficult. In this paper, we propose a general solution approach for grouping problems, i.e., reinforcement learning based local se...
متن کاملA Survey on Reinforcement Learning in Global Optimization
This report surveys recent development on the global combinatorial optimization using reinforcement learning methods. It introduces the general background of combinatorial optimization problems and reinforcement learning techniques, describes observations and previous works in this area, and focuses on Boyan and Moore's recent work, the STAGE algorithm with the assistant of reinforcement learning.
متن کاملA Reinforcement Learning Model for Solving the Folding Problem
In this paper we aim at proposing a reinforcement learning based model for solving combinatorial optimization problems. Combinatorial optimization problems are hard to solve optimally, that is why any attempt to improve their solutions is beneficent. We are particularly focusing on the bidimensional protein folding problem, a well known NP-hard optimizaton problem important within many fields i...
متن کامل