Exact Unlearning in Reinforcement Learning

Arxiv CS.LG (machine learning)

Researchers formulate the problem of exact unlearning in reinforcement learning, enabling deletion of user data from online learners upon request. The framework provides theoretical guarantees for efficient and correct data removal.

reinforcement-learning

Arxiv CS.LG (machine learning)·Thanh Nguyen-TangRaman Arora

7 days ago