← Search

Sebastian Seung

2 accepted papers

2020

Reward Prediction Error as an Exploration Objective in Deep RL

IJCAI 2020poster

A major challenge in reinforcement learning is exploration, when local dithering methods such as epsilon-greedy sampling are insufficient to solve a given task. Many recent methods have proposed to intrinsically motivate an agent to seek novel states, driving the agent to discover improved reward. H…

Cited by 0SourcePDFScholar