Research map / Bandits and online learning / RL theory and MDPs
Tractable Optimality in Episodic Latent MABs
Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor
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 EM refinement on top of tensor-decomposition initialization | tensor-decomposition baseline · Synthetic LMAB, M=7, A=50, N=100000 | per time-step reward | Improved |
| increase number of latent contexts M from 4 to 7 | ED+MLE and L-UCRL+EM · Synthetic LMAB, rank about 4 | per time-step reward | No clear effect |
| increase number of contexts M with fixed A=50, H=7 | pure tensor-decomposition method · Synthetic LMAB, rank about 4 | per time-step reward | Hurt |
| increase sampled episodes N with M=5 | ED+MLE and L-UCRL+EM · Synthetic LMAB, M=5 | per time-step reward relative to genie policy | Improved |
| use context-aware ED+MLE instead of naive UCB ignoring contexts | naive UCB · Synthetic LMAB, M=4, A=20, N=5e4 | per time-step reward | Improved |
| increase episode length H | ED+MLE, L-UCRL, tensor methods · Synthetic LMAB, M=4 | per time-step reward | Improved |
| tensor decomposition alone when covariance is full rank (M=4) | tensor-decomposition method · Synthetic LMAB, M=4, A=20 | per time-step reward | No clear effect |
Closest papers by meaning
- Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity (NeurIPS 2024 · similarity 0.87)
- Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals (ICML 2024 · similarity 0.86)
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · similarity 0.86)
- Leveraging Offline Data in Linear Latent Contextual Bandits (ICML 2025 · similarity 0.86)
- Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions (NeurIPS 2026 · similarity 0.86)
- RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation (NeurIPS 2024 · 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.
