# Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning

arXiv: https://arxiv.org/abs/1708.00102 · HTML: https://mlsanity.com/paper/1708.00102/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2017.

## Built on by (most cited first, 10 of 10)

- [Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint](https://mlsanity.com/paper/2101.07123/) (2021)
- [Maximum State Entropy Exploration using Predecessor and Successor Representations](https://mlsanity.com/paper/2306.14808/) (2023)
- [Learning Successor Features the Simple Way](https://mlsanity.com/paper/2410.22133/) (2024)
- [Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching](https://mlsanity.com/paper/2411.07007/) (2024)
- [Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience](https://mlsanity.com/paper/2208.04919/) (2022)
- [Learn Dynamic-Aware State Embedding for Transfer Learning](https://mlsanity.com/paper/2101.02230/) (2021)
- [Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features](https://mlsanity.com/paper/2405.02569/) (2024)
- [A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions](https://mlsanity.com/paper/2201.01836/) (2022)
- [Reward-Predictive Clustering](https://mlsanity.com/paper/2211.03281/) (2022)
- [Adaptive Policy Backbone via Shared Network](https://mlsanity.com/paper/2509.22310/) (2025)

## Abstract (arXiv)

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.