Research map / Reinforcement learning / RL from feedback
Model-Free Preference-Based Reinforcement Learning
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 AC-REPS with linear-programming preference IRL instead of EPMC | AC-REPS · Acrobot | median policy value: -385.2 -> -211.3 | Helped |
| use AC-REPS PBIRL instead of PF baseline | AC-REPS · Gridworld | reward | Helped |
| use exact LP approximation instead of sampled Bayesian utility estimate (ablation) | PBIRL · Gridworld | reward | Helped |
| Bayes Mean instead of LP (ablation) | PBIRL · Bicycle / SwingUp | reward | Mixed |
Closest papers by meaning
- Provable Reward-Agnostic Preference-Based Reinforcement Learning (ICLR 2024 · similarity 0.92)
- Provable Offline Preference-Based Reinforcement Learning (ICLR 2024 · similarity 0.91)
- Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning (ICLR 2025 · similarity 0.91)
- Listwise Reward Estimation for Offline Preference-based Reinforcement Learning (ICML 2024 · similarity 0.90)
- Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options (NeurIPS 2025 · similarity 0.89)
- Query-Policy Misalignment in Preference-Based Reinforcement Learning (ICLR 2024 · similarity 0.89)
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.