Transfer in Reinforcement Learning Domains

• Main Author: Taylor, Matthew E. (Author)
• Corporate Author: SpringerLink (Online service)
• Format: Electronic eBook
• Language: English
• Published: Berlin, Heidelberg : Springer Berlin Heidelberg, 2009.
• Series: Studies in Computational Intelligence, 216
• Subjects: Engineering.; Artificial intelligence.; Computational intelligence.; Computational Intelligence.; Artificial Intelligence (incl. Robotics).

In reinforcement learning (RL) problems, learning agents sequentially execute actions with the goal of maximizing a reward signal. The RL framework has gained popularity with the development of algorithms capable of mastering increasingly complex problems, but learning difficult tasks is often slow...

Table of Contents:

• Reinforcement Learning Background
• Related Work
• Empirical Domains
• Value Function Transfer via Inter-Task Mappings
• Extending Transfer via Inter-Task Mappings
• Transfer between Different Reinforcement Learning Methods
• Learning Inter-Task Mappings
• Conclusion and Future Work.