MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics

Understand

Transfer reinforcement learning (RL) aims at improving the learning efficiency of an agent by exploiting knowledge from other source agents trained on relevant tasks.

• However, it remains challenging to transfer knowledge between different environmental dynamics without having access to the source environments.
• In this work, we explore a new challenge in transfer RL, where only a set of source policies collected under diverse unknown dynamics is available for learning a target task efficiently.
• To address this problem, the proposed approach, MULTI-source POLicy AggRegation (MULTIPOLAR), comprises two key techniques.