Information-Directed Exploration for Deep Reinforcement Learning

ICLR 2019 Nikolay NikolovJohannes KirschnerFelix BerkenkampAndreas Krause

Efficient exploration remains a major challenge for reinforcement learning. One reason is that the variability of the returns often depends on the current state and action, and is therefore heteroscedastic... (read more)

PDF Abstract

Evaluation Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.