learning, neural networks, robotics, AI, and engineering. In recognition of the growing importance of reinforcement learning, it seemed an opportune time to bring together leading researchers from these areas for a three-day meeting consisting of general and wide-ranging discussions. The National Science Foundation (NSF) sponsored the workshop with a generous grant to cover the travel and lodgi...

Based on the previously proposed extended neural-fuzzy network, this paper presents a cooperation scheme of training data based learning and reinforcement learning for constructing sensor-based behaviour modules in robot navigation. In order to solve reinforcement learning problem, a reinforcement-based neural-fuzzy control system (RNFCS) is provided, which consists of a neural-fuzzy controller...

A general technique is proposed for embedding online clustering algorithms based on competitive learning in a reinforcement learning framework. The basic idea is that the clustering system can be viewed as a reinforcement learning system that learns through reinforcements to follow the clustering strategy we wish to implement. In this sense, the reinforcement guided competitive learning (RGCL) ...

ion and Generalization in Reinforcement Learning: A Summary and Framework Marc Ponsen, Matthew E. Taylor, and Karl Tuyls 1 Universiteit Maastricht, Maastricht, The Netherlands {m.ponsen,k.tuyls}@maastrichtuniversity.nl 2 The University of Southern California, Los Angeles, CA [email protected] Abstract. In this paper we survey the basics of reinforcement learning, generalization and abstraction. W...

A novel integrative learning architecture, RLSM with a STDP network is described. This architecture models symbol emergence in an autonomous agent engaged in reinforcement learning tasks. The architecture consists of two constitutional learning architectures: a reinforcement learning schema model (RLSM) and a spike timing-dependent plasticity (STDP) network. RLSM is an incremental modular reinf...

This paper presents a direct reinforcement learning algorithm, called Finite-Element Reinforcement Learning, in the continuous case, i.e. continuous state-space and time. The evaluation of the value function enables the generation of an optimal policy for reinforcement control problems, such as target or obstacle problems, viability problems or optimization problems. We propose a continuous for...

Recently, the interest in reinforcement learning in game playing has been renewed. This is evidenced by the groundbreaking results achieved by AlphaGo. General Game Playing (GGP) provides a good testbed for reinforcement learning, currently one of the hottest fields of AI. In GGP, a specification of games rules is given. The description specifies a reinforcement learning problem, leaving progra...

The \forward modeling" approach of Jor-dan and Rumelhart has been shown to be applicable when supervised learning methods are to be used for solving reinforcement learning tasks. Because such tasks are natural candidates for the application of reinforcement learning methods, there is a need to evaluate the relative merits of these two learning methods on reinforcement learning tasks. We present...