Skip to yearly menu bar Skip to main content

Invited Talk
Workshop: Intrinsically Motivated Open-ended Learning (IMOL) Workshop

Georg Martius - Intrinsic Motivations for Efficient Exploration in Reinforcement Learning

[ ]
Sat 16 Dec 6:25 a.m. PST — 7:05 a.m. PST


I will summarize research in the area of intrinsic motivation in the context of learning and exploration and touch upon open-ended learning in the IMOL community. I will then present our recent work on combining different intrinsic motivation signals with reinforcement learning, such as learning progress, causal influence and information gain. A particular exciting direction is to employ model-based reinforcement learning to make robots learn by freely playing how to interact effectively driven by information gain and other generic drives. We find that this leads to high zero-shot generalization to new tasks.

Chat is not available.