Research map / Bandits and online learning / RL theory and MDPs
Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret
Jiawei Huang, Li Zhao, Tao Qin, Wei Chen, Nan Jiang, Tie-Yan Liu
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 Pessimistic Value Iteration as the exploitation algorithm for risk-averse users | Tiered RL (Alg^E) · Gap-dependent tabular MDPs | regret of risk-averse users | Improved |
| Separate exploitation and online policies in the gap-independent setting | Tiered RL · Gap-independent minimax | regret of risk-averse users | No clear effect |
| Keep the online policy running while the exploitation policy uses pessimism | Alg^O in tiered RL · Gap-dependent tabular MDPs | regret of online users | No clear effect |
| Use LCB with UCB online policy in stochastic bandits | Tiered bandits · Stochastic multi-armed bandits | regret of exploitation users | Improved |
Closest papers by meaning
- Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning (ICML 2024 · similarity 0.89)
- The Regret of Exploration and the Control of Bad Episodes in Reinforcement Learning (ICML 2023 · similarity 0.89)
- Robust Knowledge Transfer in Tiered Reinforcement Learning (NeurIPS 2023 · similarity 0.88)
- Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret (NeurIPS 2020 · similarity 0.88)
- Minimax Optimal Reinforcement Learning with Quasi-Optimism (ICLR 2025 · similarity 0.88)
- Position: Constants are Critical in Regret Bounds for 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.
