Research map / Reinforcement learning / Visual and representation RL
Eigenoption Discovery through the Deep Successor Representation
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 |
|---|---|---|---|
| use eigenoptions learned from the successor representation instead of primitive actions alone | Q-learning in the Rooms domain · Rooms | control performance | Helped |
| add eigenoptions learned from the successor representation | uniform-random exploration in the Rooms domain · Rooms | diffusion time | Helped |
| learn the successor representation for more episodes | successor-representation eigenoption discovery · Rooms | successor-representation estimate accuracy | Helped |
| learn the successor representation for more episodes | successor-representation eigenoption discovery · Rooms | control performance | Helped |
| use eigenoptions learned from raw pixels | greedy one-step eigenoption policies · Bank Heist, Montezuma's Revenge, and Ms. Pac-Man | purposeful state navigation | Helped |
| use greedy one-step policies to learn eigenoptions | successor-representation eigenoption discovery · Freeway | option effectiveness | Hurt |
Closest papers by meaning
- A Laplacian Framework for Option Discovery in Reinforcement Learning (ICML 2017 · similarity 0.91)
- Deep Laplacian-based Options for Temporally-Extended Exploration (ICML 2023 · similarity 0.89)
- Online Laplacian-Based Representation Learning in Reinforcement Learning (ICML 2025 · similarity 0.87)
- Reward-Aware Proto-Representations in Reinforcement Learning (NeurIPS 2025 · similarity 0.85)
- Towards Principled Representation Learning from Videos for Reinforcement Learning (ICLR 2024 · similarity 0.85)
- Diffusion Spectral Representation for Reinforcement Learning (NeurIPS 2024 · similarity 0.85)
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.