Q-learning Approach in the Context of Virtual Learning Environment
Liviu Ioniţă, Irina Tudor · 2008
Reinforcement learning (RL) is learning what to do (how to map situations to actions) to maximize a numerical reward signal. Two characteristics: trial-and-error search and delayed reward are the two most important features of reinforcement learning. RL is different from supervised learning, the kind of learning studied in most current research in machine learning, statistical pattern recognition, and artificial neural networks. A learning problem can be solved by an intelligent agent in the context of reinforcement learning. In this case, to obtain a lot of reward, a reinforcement learning agent must prefer actions that it has tried in the past and found to be effective in producing reward. In our paper we present our investigation of Q-learning (Reinforcement Learning) in the context of Virtual Learning Environment.