Research map / Reinforcement learning / MDPs and planning
Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning
Dingwen Kong, Lin Yang
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 |
|---|---|---|---|
| choose reward queries actively instead of uniformly sampling from the exploration dataset (ablation) | reward-free exploration plus reward learning algorithm · random two-stage tabular MDP (S=20, A=10/3), noise margin 0.05 | queries needed for target policy accuracy | Improved |
| vary the noise margin Delta with N=100 queries fixed | active reward learning algorithm · random two-stage tabular MDP, d=5, K=2000 | policy error V1*(s1) - V1(s1) | Mixed |
| compare active vs passive learning across noise margins (ablation) | active reward learning algorithm · random two-stage tabular MDP, N=100 queries | policy error | Improved |
Closest papers by meaning
- Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning (ICLR 2025 · similarity 0.91)
- Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization (ICML 2024 · similarity 0.91)
- DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement Learning from Human Feedback (AAAI 2025 · similarity 0.91)
- A Theoretical Framework for Partially-Observed Reward States in RLHF (ICLR 2025 · similarity 0.90)
- Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference (ICLR 2025 · similarity 0.90)
- Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective (ICML 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.
