Research map / Reinforcement learning / Visual and representation RL
Information Prioritization through Empowerment in Visual Model-based RL
Homanga Bharadhwaj, Mohammad Babaeizadeh, Dumitru Erhan, Sergey Levine
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 |
|---|---|---|---|
| Add empowerment to representation and policy learning | InfoPower · Vision-based control with natural video distractors | episodic return: up to 20\% better performance in terms of cumulative rewards at 1M environment interactions | Improved |
| Remove empowerment from policy optimization (ablation) | InfoPower · Natural video distractors, especially sparse-reward tasks before 200k interactions | episodic return | Hurt |
| Use the NCE mutual-information bound instead of the NWJ bound (ablation) | InfoPower · DeepMind Control tasks with natural video distractors | episodic return | No clear effect |
| Increase distractor-window level from L1 to L3 | InfoPower · DM Control Walker Stand | Rew@1M: 650\pm100 -> 624\pm80 | Hurt |
Closest papers by meaning
- The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning (NeurIPS 2026 · similarity 0.88)
- Focus On What Matters: Separated Models For Visual-Based RL Generalization (NeurIPS 2024 · similarity 0.88)
- Causal Information Prioritization for Efficient Reinforcement Learning (ICLR 2025 · similarity 0.88)
- DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization (ICLR 2024 · similarity 0.88)
- MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning (ICML 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.
