… We introduce the use of learned shaping rewards in reinforcement learning tasks, where
an agent uses prior experience on a sequence of tasks to learn a portable predictor that …

… We have introduced a framework for studying knowledge transfer in reinforcement learning
in which the learning agent has to solve different tasks drawn from a given distribution. This …

… from agent-centric to environment-centric learning systems. Using several example … our
knowledge transfer approach can allow faster and lower cost learning than existing alternatives. …

… In this work, we have proposed a knowledge transfer algorithm for RL. The REPAINT algorithm
performs an onpolicy representation transfer for the pre-trained teacher policies and an off…

… 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 …

… the learning of a new task. Our results indicate that TL can greatly accelerate DRL when
transferring knowledge … tasks plays a key role in the success or failure of knowledge transfer. …

… 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 …

… -level performance in multiple different tasks by learning from task-specific teachers. In …
knowledge transfer algorithm designed particularly for the actor-critic architecture to quickly learn …

… lifelong reinforcement learning (RL) has been limited to learning from … Knowledge transfer
between tasks has been explored in the context of transfer learning and multi-task learning. In …

… by introducing Transfer Learning (TL) capabilities. This survey addresses strategies of
knowledge transfer from simple parameter sharing to privacy preserving federated learning and …