ServiceNow Research

Offline Reinforcement Learning

Using Confounded Data in Offline RL
Using Confounded Data in Offline RL
In this work we consider the problem of confounding in offline RL, also referred to as the delusion problem. While it is known that …
Workshop at the Neural Information Processing Systems (NeurIPS),  2022.
PDF Cite Code Slides Video
A Probabilistic Perspective on Reinforcement Learning via Supervised Learning
A Probabilistic Perspective on Reinforcement Learning via Supervised Learning
Reinforcement Learning via Supervised Learning (RvS) only uses supervised techniques to learn desirable behaviors from large datasets. …
Workshop at the International Conference on Learning Representations (ICLR),  2022.
PDF Cite Code