Timezone: »

See, Hear, Explore: Curiosity via Audio-Visual Association
Victoria Dean · Shubham Tulsiani · Abhinav Gupta

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #355

Exploration is one of the core challenges in reinforcement learning. A common formulation of curiosity-driven exploration uses the difference between the real future and the future predicted by a learned model. However, predicting the future is an inherently difficult task which can be ill-posed in the face of stochasticity. In this paper, we introduce an alternative form of curiosity that rewards novel associations between different senses. Our approach exploits multiple modalities to provide a stronger signal for more efficient exploration. Our method is inspired by the fact that, for humans, both sight and sound play a critical role in exploration. We present results on several Atari environments and Habitat (a photorealistic navigation simulator), showing the benefits of using an audio-visual association model for intrinsically guiding learning agents in the absence of external rewards. For videos and code, see https://vdean.github.io/audio-curiosity.html.

Author Information

Victoria Dean (Carnegie Mellon University)
Shubham Tulsiani (Facebook AI Research)
Abhinav Gupta (Facebook AI Research/CMU)

More from the Same Authors