Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning
arXiv:1708.00102
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.
References in corpus (2)
Cited by in corpus (6)
- Transfer Learning in Deep Reinforcement Learning: A Survey
- UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning
- State2vec: Off-Policy Successor Features Approximators
- Transfer with Model Features in Reinforcement Learning
- SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning
- Learn Dynamic-Aware State Embedding for Transfer Learning