Research map / Bandits and online learning / RL theory and MDPs
Randomized Exploration in Reinforcement Learning with General Value Function Approximation
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 |
|---|---|---|---|
| Use multiple independently reward-perturbed regressions and take the maximum estimate | LSVI-PHE · 12-state RiverSwim, H=40 | per-episode return | No clear effect |
| Use multiple independently reward-perturbed regressions and take the maximum estimate | LSVI-PHE · 10×10 DeepSea | per-episode return | No clear effect |
| Increase the number of perturbation samples M (ablation) | LSVI-PHE · 10×10 DeepSea | per-episode return | Helped |
| Set M=1 and σ²=1, reducing optimistic reward sampling to RLSVI (ablation) | LSVI-PHE · Hard exploration tasks | performance | No clear effect |
Closest papers by meaning
- Generalization and Exploration via Randomized Value Functions (ICML 2016 · similarity 0.94)
- Beyond Optimism: Exploration With Partially Observable Rewards (NeurIPS 2024 · similarity 0.91)
- Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning (ICLR 2024 · similarity 0.90)
- Minimax Optimal Reinforcement Learning with Quasi-Optimism (ICLR 2025 · similarity 0.90)
- Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation (NeurIPS 2024 · similarity 0.90)
- Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL (NeurIPS 2025 · 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.