Research map / Reinforcement learning / RL from feedback
Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF
Han Shen, Zhuoran Yang, Tianyi Chen
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 PBRL with the value penalty instead of independent policy gradient | Stackelberg Markov game · Randomly generated MDPs | leader's total reward | Improved |
| Use PBRL with the Bellman penalty instead of independent policy gradient | Stackelberg Markov game · Randomly generated MDPs | leader's total reward | Improved |
| Use PBRL instead of DRLHF | RLHF · Seaquest | episode return | No clear effect |
| Use PBRL instead of DRLHF | RLHF · BeamRider | episode return | Improved |
| Use PBRL instead of DRLHF | RLHF · MsPacman | episode return | Improved |
| Use PBRL instead of Meta-Gradient | Bilevel RL for incentive design · Random environments | designer's reward | Improved |
Closest papers by meaning
- Contextual Bilevel Reinforcement Learning for Incentive Alignment (NeurIPS 2024 · similarity 0.91)
- PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback (ICLR 2024 · similarity 0.90)
- Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization (ICML 2024 · similarity 0.88)
- Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator (NeurIPS 2024 · similarity 0.87)
- Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference (ICLR 2025 · similarity 0.87)
- A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning (NeurIPS 2026 · 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.
