… the application of Transfer Learning (TL) to … transferring knowledge from similar tasks, and
that the similarity between tasks plays a key role in the success or failure of knowledge transfer…

… We now describe our knowledge transfer algorithm, ie, REPAINT, for actor-critic RL … PPO,
and use a single teacher policy in the knowledge transfer. In practice, it can be directly applied …

… , along with two existing methods, enabling knowledge transfer in … deep reinforcement
learning algorithms. We further show that dispatching policies learned by transferring knowledge …

… In this work, we investigate knowledge transfer for deep reinforcement learning. On one hand,
we propose a new architecture for policy network, which introduces significant reduction in …

… a Knowledge Transfer based Multi-task Deep Reinforcement … leverages an offline knowledge
transfer algorithm designed … of KTM-DRL and its knowledge transfer and online learning …

… In this paper, we explore the use of knowledge graphs as a representation for domain
knowledge transfer for training text-adventure playing reinforcement learning agents. Our methods …

… We also investigate TL approaches by the way that knowledge transfer occurs, such as
inter-task mapping (Section 5.4), or learning transferrable representations (Section 5.5), etc. We …

… Reinforcement Learning (RL) has prompted researchers to start developing a greater interest
in systematic approaches to retain and reuse knowledge … for knowledge transfer which has …

… In this paper, an improve reinforcement learning framework fusing knowledge transfer has
been developed to improve the learning performance in complex target domains by resorting …

This paper presents an end-to-end online learning navigation method based on deep
reinforcement learning (DRL) for mobile robots, whose objective is that mobile robots can avoid …