Research map / Reinforcement learning / Visual and representation RL
Temporal Abstraction in Reinforcement Learning with the Successor Representation
Marlos C. Machado, Andre Barreto, Doina Precup, Michael Bowling
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 (top several SR eigenvectors, broad initiation) instead of covering options | Q-learning with epsilon-greedy exploration · Four-room (reward maximization) | learning speed | Improved |
| add covering options to the agent's action set | Q-learning with epsilon-greedy exploration · Four-room (reward maximization) | learning speed | No clear effect |
| use more than one eigenvector per iteration (eigenoptions rather than covering options) (ablation) | option discovery from the SR · Four-room (closed form, diffusion time) | diffusion time | Improved |
| give options a broad initiation set instead of a single state (ablation) | covering options · Four-room (closed form, diffusion time) | diffusion time | Mixed |
| estimate the SR online with TD learning instead of closed form | eigenoptions · Four-room (online, diffusion time) | diffusion time | No clear effect |
| estimate the SR online with TD learning instead of closed form | covering options · Four-room (online, diffusion time) | average diffusion time | Hurt |
| add covering options (even a single option) to primitive actions | random walk · Four-room (closed form, median diffusion time) | median diffusion time | Improved |
| add few eigenoptions (small option budget) | random walk · Four-room (closed form, average diffusion time) | average diffusion time | Hurt |
| use SR eigenvectors instead of proto-value functions for covering options (ablation) | covering options · Four-room (appendix) | diffusion time | No clear effect |
Closest papers by meaning
- Representation-driven Option Discovery in Reinforcement Learning (AAAI 2025 · similarity 0.93)
- Autonomous Option Invention for Continual Hierarchical Reinforcement Learning and Planning (AAAI 2025 · similarity 0.90)
- Reward-Aware Proto-Representations in Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
- Reward-Respecting Subtasks for Model-Based Reinforcement Learning (Abstract Reprint) (AAAI 2024 · similarity 0.88)
- Bridging State and History Representations: Understanding Self-Predictive RL (ICLR 2024 · similarity 0.87)
- OptionZero: Planning with Learned Options (ICLR 2025 · similarity 0.87)
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.
