Research map / Bandits and online learning / RL theory and MDPs
Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR
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 |
|---|---|---|---|
| Bernstein bonus (with sqrt(tau) variance term and 1/N term) instead of Hoeffding bonus in CVaR UCB | CVaR MAB (Bernstein-UCB) · MAB CVaR regret | regret rate | Helped |
| Bernstein bonus instead of Hoeffding bonus in CVaR-UCBVI | tabular CVaR RL (CVaR-UCBVI) · RL CVaR regret | leading term in regret bound: τ^-1√(SAHK) to τ^-1√(SAK), an S√H improvement | Helped |
| Assume continuous returns with lower-bounded density | CVaR-UCBVI with Bernstein bonus · RL CVaR regret | leading term in regret bound: τ^-1√(SAK) to √(τ^-1SAK), matching lower bound | Helped |
| Discretize rewards to an η-grid (η=1/√K) for computational efficiency | CVaR-UCBVI · RL CVaR regret | regret and runtime | No clear effect |
Closest papers by meaning
- Risk-Sensitive Reward-Free Reinforcement Learning with CVaR (ICML 2024 · similarity 0.92)
- Provably Efficient CVaR RL in Low-rank MDPs (ICLR 2024 · similarity 0.92)
- A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents (ICML 2025 · similarity 0.92)
- Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback (ICLR 2024 · similarity 0.90)
- Online Learning in Risk Sensitive constrained MDP (ICML 2025 · similarity 0.90)
- Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning (ICML 2024 · similarity 0.90)
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.