15th European Conference on Artificial Intelligence
  July 21-26 2002     Lyon     France  
   

ECAI-2002 Conference Paper

[PDF] [full paper] [prev] [tofc] [next]

Reinforcement Learning Integrated with a Non-Markovian Controller

Istvan Szita, Balint Takacs, Andras Lorincz

Recently a novel reinforcement learning algorithm called event-learning or E-learning was introduced. The algorithm based on events, which are defined as ordered pairs of states. In this setting, the agent optimizes the selection of desired sub-goals by a traditional value-policy function iteration, and utilizes a separated algorithm called the controller to achieve these goals. The advantage of event-learning lies in its potential in non-stationary environments, where the near-optimality of the value iteration is guaranteed by the generalized epsilon-stationary MDP model. Using a particular non-Markovian controller, the SDS controller, an epsilon-MDP problem arises in E-learning. We illustrate the properties of E-learning augmented by the SDS controller by computer simulations.

Keywords: Reinforcement Learning, Machine Learning, Robotics

Citation: Istvan Szita, Balint Takacs, Andras Lorincz: Reinforcement Learning Integrated with a Non-Markovian Controller. In F. van Harmelen (ed.): ECAI2002, Proceedings of the 15th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2002, pp.365-369.


[prev] [tofc] [next]


ECAI-2002 is organised by the European Coordinating Committee for Artificial Intelligence (ECCAI) and hosted by the UniversitÚ Claude Bernard and INSA, Lyon, on behalf of Association Franšaise pour l'Intelligence Artificielle.