Research map / Multi-agent systems and games / Human-AI and goal-conditioned
The Value of Information When Deciding What to Learn
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 adaptive beta_t equal to inverse best information ratio instead of fixed beta | variance-BLAIDS · 50-arm Bernoulli and Gaussian bandits | cumulative regret | Improved |
| add information-directed acquisition (variance-BLAIDS) instead of Thompson-sampling-style BLASTS | BLASTS · 50-arm Bernoulli and Gaussian bandits | cumulative regret | Improved |
| lower beta with variance-BLAIDS instead of variance-IDS | variance-BLAIDS · Bernoulli bandit | cumulative regret | Improved |
| lower beta with variance-BLAIDS instead of variance-IDS | variance-BLAIDS · Gaussian bandit | cumulative regret | No clear effect |
| compute target action with Blahut-Arimoto instead of hand-crafted epsilon-optimal target (STS) | BLASTS · 50-arm Bernoulli and Gaussian bandits | information-performance trade-off | Improved |
Closest papers by meaning
- Deciding What to Learn: A Rate-Distortion Approach (ICML 2021 · similarity 0.93)
- Information Acquisition Under Resource Limitations in a Noisy Environment (AAAI 2018 · similarity 0.87)
- Evolution of Information in Interactive Decision Making: A Case Study for Multi-Armed Bandits (NeurIPS 2025 · similarity 0.86)
- Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory (NeurIPS 2026 · similarity 0.85)
- Online Information Acquisition: Hiring Multiple Agents (ICLR 2024 · similarity 0.85)
- On Bits and Bandits: Quantifying the Regret-Information Trade-off (ICLR 2025 · 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.
