Research map / Reinforcement learning / Offline RL
Kernel Value Regression in Offline Reinforcement Learning
Jongyeon Lee, Jaehyoung Jeon, Kim Haneol, Myungjoo Kang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Addresses value overestimation in offline RL by a kernel value regression approach; abstract is truncated so details beyond the problem framing are unknown.
Problem
Value overestimation in offline reinforcement learning, where Bellman backups propagate out-of-distribution errors that inflate Q-values; prior policy-constraint methods yield suboptimal policies or add training complexity.
Approach
Unknown from the truncated abstract; the title suggests regressing values with kernel methods rather than standard parametric Q-function regression.
Limitations
- Only the truncated abstract was available; method details and results are unknown.
Closest papers by meaning
- A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning (AAAI 2024 · similarity 0.89)
- Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning (ICML 2024 · similarity 0.89)
- Iteratively Refined Behavior Regularization for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- Is Value Learning Really the Main Bottleneck in Offline RL? (NeurIPS 2024 · similarity 0.89)
- Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm (NeurIPS 2024 · similarity 0.88)
- Doubly Mild Generalization for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
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.
