Advantages And Limitations Of Using Successor Features For Transfer In Reinforcement Learning

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylehnert2017advantages

Related papers

• Successor Feature Representations (2021)0.00
• Transfer With Model Features In Reinforcement Learning (2018)0.00
• Successor Features For Transfer In Reinforcement Learning (2016)0.00
• A New Representation Of Successor Features For Transfer Across Dissimilar Environments (2021)0.00
• Successor Features Combine Elements Of Model-free And Model-based Reinforcement Learning (2019)0.00
• Successor Feature Sets: Generalizing Successor Representations Across Policies (2021)5.84
• Universal Successor Representations For Transfer Reinforcement Learning (2018)0.00
• SF-DQN: Provable Knowledge Transfer Using Successor Feature For Deep Reinforcement Learning (2024)0.00