Research map / Reinforcement learning / RL from feedback
Preference-based Reinforcement Learning with Finite-Time Guarantees
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 PEPS instead of DPS or EPMC | PbRL policy recovery · Grid World and Random MDP with BTL preferences | optimal policy recovery | Helped |
| Use PEPS with near-deterministic preferences (c=0.001) | PbRL policy recovery · Grid World | optimal policy recovery | Helped |
| Use PEPS instead of DPS or EPMC | PbRL policy recovery · Random MDP with BTL preferences | optimal policy recovery | Helped |
| Use PEPS with very noisy linear preferences | PbRL policy recovery · Grid World | optimal policy recovery | No clear effect |
| Use PEPS with very noisy linear preferences | PbRL policy recovery · Random MDP | optimal policy recovery | Helped |
| Use PEPS with deterministic preferences | PbRL policy recovery · Grid World and Random MDP | optimal policy recovery | Helped |
| Increase the BTL parameter c | PEPS · Grid World and Random MDP | optimal policy recovery | No clear effect |
| Use synthetic-reward-guided exploration with dueling-bandit policy search | PEPS · PbRL without a simulator | steps | Helped |
| Replace EULER with Q-learning in the fixed-budget experiments | PEPS · Synthetic environments | computational efficiency | Helped |
Closest papers by meaning
- Provable Reward-Agnostic Preference-Based Reinforcement Learning (ICLR 2024 · similarity 0.93)
- Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning (ICLR 2025 · similarity 0.91)
- Decoding Global Preferences: Temporal and Cooperative Dependency Modeling in Multi-Agent Preference-Based Reinforcement Learning (AAAI 2024 · similarity 0.90)
- Provable Offline Preference-Based Reinforcement Learning (ICLR 2024 · similarity 0.90)
- Efficient Preference-Based Reinforcement Learning: Randomized Exploration meets Experimental Design (NeurIPS 2025 · similarity 0.90)
- RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning (NeurIPS 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.