Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning
This work addresses the challenge of knowledge transfer in reinforcement learning for researchers and practitioners, but it appears incremental as it focuses on evaluating an existing method rather than introducing new paradigms.
The paper tackles the problem of learning feature representations for scaling and knowledge transfer in reinforcement learning by implementing a method that decouples features from reward functions using Successor Features, and it assesses the advantages and limitations of this approach without providing specific numerical results.
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 Features approach this problem by learning a feature representation that satisfies a temporal constraint. We present an implementation of an approach that decouples the feature representation from the reward function, making it suitable for transferring knowledge between domains. We then assess the advantages and limitations of using Successor Features for transfer.