Recently, there has been a focus on using transfer learning to reduce the sample complexity
in reinforcement learning. One component that enables transfer is an intertask mapping that …

The goal of transfer learning algorithms is to utilize knowledge gained in a source task to
speed up learning in a different but related target task. Recently, several transfer methods for …

One question central to Reinforcement Learning is how to learn a feature representation that
supports algorithm scaling and re-use of learned information from different tasks. Successor …

In deep reinforcement learning (RL) research, there has been a concerted effort to design
more efficient and productive exploration methods while solving sparse-reward problems …

Reinforcement learning algorithms require an extensive number of samples to perform a
specific task. To achieve the same performance on a new task, the agent must learn from …

A key question in Reinforcement Learning is which representation an agent can learn to
efficiently reuse knowledge between different tasks. Recently the Successor Representation …

Recent work in transfer learning has succeeded in making reinforcement learning
algorithms more efficient by incorporating knowledge from previous tasks. However, such …

■ Transfer learning has recently gained popularity due to the development of algorithms
that can successfully generalize information across multiple tasks. This article focuses on …

In recent years, a variety of transfer learning (TL) methods have been developed in the
context of reinforcement learning (RL) tasks. Typically, when an RL agent leverages TL, it …

In this paper we investigate using multiple mappings for transfer learning in reinforcement
learning tasks. We propose two different transfer learning algorithms that are able to …