Research map / Multi-agent systems and games / Games and equilibria
Deciding What to Learn: A Rate-Distortion Approach
Dilip Arumugam, Benjamin Van Roy
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 BLASTS to choose rate-distortion target actions instead of sampling optimal actions directly | Thompson sampling for independent Bernoulli and Gaussian bandits · Independent Bernoulli bandits | cumulative regret | Improved |
| Use BLASTS to choose rate-distortion target actions instead of sampling optimal actions directly | Thompson sampling for independent Bernoulli and Gaussian bandits · Independent Gaussian bandits | cumulative regret | Improved |
| Set beta near zero (ablation) | BLASTS · Independent Bernoulli and Gaussian bandits | policy behavior | Hurt |
| Set beta toward infinity (ablation) | BLASTS · Independent Bernoulli and Gaussian bandits | policy behavior | No clear effect |
| Adapt beta each time period using the inverse minimized variance-based information ratio (ablation) | BLASTS · Independent Bernoulli bandits | optimal-policy identification | Improved |
| Adapt beta each time period using the inverse minimized variance-based information ratio (ablation) | BLASTS · Independent Gaussian bandits | optimal-policy identification | Improved |
Closest papers by meaning
- Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory (NeurIPS 2026 · similarity 0.88)
- A Minimaximalist Approach to Reinforcement Learning from Human Feedback (ICML 2024 · similarity 0.88)
- Refining Minimax Regret for Unsupervised Environment Design (ICML 2024 · similarity 0.87)
- Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias (NeurIPS 2026 · similarity 0.87)
- Multi-Agent Imitation Learning: Value is Easy, Regret is Hard (NeurIPS 2024 · similarity 0.87)
- Every Bit Helps: Achieving the Optimal Distortion with a Few Queries (AAAI 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.
