See, Hear, Explore: Curiosity via Audio-Visual Association
arXiv:2007.03669
Abstract
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.
References in corpus (11)
- Auto-Encoding Variational Bayes
- The Replica Dataset: A Digital Replica of Indoor Spaces
- More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch
- #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
- Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
- Reinforcement Learning with Unsupervised Auxiliary Tasks
- Go-Explore: a New Approach for Hard-Exploration Problems
- Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning
- Loss is its own Reward: Self-Supervision for Reinforcement Learning
- Gotta Learn Fast: A New Benchmark for Generalization in RL
- Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment