Research map / Reinforcement learning / Visual and representation RL
Successor Feature Sets: Generalizing Successor Representations Across Policies
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Increase the number of retained boundary points (ablation) | Approximate successor feature set dynamic programming · Mountain-car and gridworld domains | Bellman error | Helped |
| Use the approximation in domains with more features and uncertainty | Approximate successor feature set dynamic programming · Gridworld domains | Bellman error | Hurt |
| Evaluate directions not optimized for during backups | Approximate successor feature set dynamic programming · Mountain-car and gridworld domains | Bellman error | Hurt |
Closest papers by meaning
- Reward-Aware Proto-Representations in Reinforcement Learning (NeurIPS 2025 · similarity 0.93)
- Learning Successor Features the Simple Way (NeurIPS 2024 · similarity 0.91)
- A Distributional Analogue to the Successor Representation (ICML 2024 · similarity 0.90)
- Distributional Successor Features Enable Zero-Shot Policy Optimization (NeurIPS 2024 · similarity 0.90)
- $\pi$2vec: Policy Representation with Successor Features (ICLR 2024 · similarity 0.89)
- Bridging State and History Representations: Understanding Self-Predictive RL (ICLR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.