Research map / Probabilistic and scientific modeling / Bayesian optimization
Counterfactual Data-Fusion for Online Reinforcement Learners
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 |
|---|---|---|---|
| Fuse observational and experimental data with counterfactual data (TSRDC* vs TSRDC+) (ablation) | TSRDC+ · Greedy Casino | cumulative regret: 65.04 -> 42.23 | Helped |
| Fuse observational and experimental data with counterfactual data (TSRDC* vs TSRDC+) (ablation) | TSRDC+ · Paradoxical Switching | cumulative regret: 64.70 -> 36.91 | Helped |
| Replace intent-agnostic TS with RDC-based players | TS · Greedy Casino | optimal arm convergence | Helped |
| Vary reward parameterization across a wide range | TSRDC* · Appendix B parameterizations | cumulative regret | Helped |
Closest papers by meaning
- Robustly Improving Bandit Algorithms with Confounded and Selection Biased Offline Data: A Causal Approach (AAAI 2024 · similarity 0.90)
- Leveraging (Biased) Information: Multi-armed Bandits with Offline Data (ICML 2024 · similarity 0.88)
- The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models (AAAI 2024 · similarity 0.88)
- Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals (ICML 2024 · similarity 0.87)
- Multi-Armed Bandits with Interference: Bridging Causal Inference and Adversarial Bandits (ICML 2025 · similarity 0.87)
- Information-Directed Offline-to-Online Reinforcement Learning (NeurIPS 2026 · 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.