Research map / Reinforcement learning / Visual and representation RL
A New Representation of Successor Features for Transfer across Dissimilar Environments
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 |
|---|---|---|---|
| Model source successor features as noisy measurements of target successor features with Gaussian Processes, then use GPI | SFDE · Toy navigation maze | performance | Helped |
| Model source successor features as noisy measurements of target successor features with Gaussian Processes, then use GPI | SFDE · CartPole-v0 | performance | Helped |
| Model source successor features as noisy measurements of target successor features with Gaussian Processes, then use GPI | SFDE · FSF environment | average reward | Helped |
| Fine-tune source successor features on target observations | FSF · FSF environment, adaptation phase | average reward | Helped |
| Use linear projection to map source successor features to target successor features | LPSF · Toy navigation maze | speed of successor-feature updating | Hurt |
Closest papers by meaning
- Distributional Successor Features Enable Zero-Shot Policy Optimization (NeurIPS 2024 · similarity 0.89)
- Reward-Aware Proto-Representations in Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
- Learning Successor Features the Simple Way (NeurIPS 2024 · similarity 0.88)
- A Distributional Analogue to the Successor Representation (ICML 2024 · similarity 0.88)
- SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning (ICML 2024 · similarity 0.87)
- Proto Successor Measure: Representing the Behavior Space of an RL Agent (ICML 2025 · similarity 0.86)
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.
