Intelligent virtual environments: Operating conditioning and observational learning in agents using neural networks

Virtual environments are frequently used for simulation where situations with many agents interact among them with or without user interaction. In many cases, intelligence is required to the agents, meaning not only ability to sense the environment, make decisions and as a result act, but also including learning ability. On the other hand, in psychology field, several studies have been made - including both human observation and animal experimentation - and as a result, many different theories about learning have been formulated, such as classing conditioning, operating conditioning, cognitive learning and observational learning. This paper has as the objective of applying some of these psychology concepts to intelligent virtual agents field. With this purpose we developed a virtual environment where the agent's interaction takes place. Learning abilities are also incorporated to them using neural networks. Finally, results are presented and conclusions extracted