MOPO: Model-based Offline Policy Optimization

Nov-14-2025, 21:04:09 GMT–Neural Information Processing Systems

However, standard model-based RL methods, designed for the online setting, do not provide an explicit mechanism to avoid the offline setting's distributional shift issue.

arxiv preprint arxiv, machine learning, reinforcement learning, (13 more...)

Neural Information Processing Systems

Nov-14-2025, 21:04:09 GMT

Conferences PDF

Country:
- Asia > China
  - Shandong Province > Dongying (0.04)
- North America
  - Canada (0.04)
  - United States
    - California > Santa Clara County
      - Palo Alto (0.04)
    - Massachusetts (0.04)

Genre:
- Research Report (0.68)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Neural Networks (0.68)
    - Reinforcement Learning (1.00)
  - Representation & Reasoning (1.00)
  - Robots (1.00)