Representation transfer for reinforcement learning

Transfer learning problems are typically framed as leveraging knowledge learned on a source task to improve learning on a related, but different, target task. Current transfer learning methods are able to successfully transfer knowledge from a source reinforcement learning task into a target task, reducing learning time. However, the complimentary task of transfer-ring knowledge between agents with different internal repre-sentations has not been well explored. The goal in both types of transfer problems is the same: reduce the time needed to learn the target with transfer, relative to learning the target without transfer. This work defines representation transfer, contrasts it with task transfer, and introduces two novel al-gorithms. Additionally, we show representation transfer al-gorithms can also be successfully used for task transfer, pro-viding an empirical connection between the two problems. These algorithms are fully implemented in a complex multi-agent domain and experiments demonstrate that transferring the learned knowledge between different representations is both possible and beneficial