Noisy Agents: Self-supervised Exploration by Predicting Auditory Events

TL;DR

This paper introduces a novel intrinsic motivation for reinforcement learning that uses auditory event prediction to enhance exploration, leading to improved performance and emergent physical interaction behaviors in agents.

Contribution

The work proposes a new intrinsic reward based on auditory event prediction, combining clustering and neural prediction to improve RL exploration.

Findings

Outperforms state-of-the-art baselines in Atari games

Leads to emergence of physical interaction behaviors

Enhances exploration efficiency

Abstract

Humans integrate multiple sensory modalities (e.g. visual and audio) to build a causal understanding of the physical world. In this work, we propose a novel type of intrinsic motivation for Reinforcement Learning (RL) that encourages the agent to understand the causal effect of its actions through auditory event prediction. First, we allow the agent to collect a small amount of acoustic data and use K-means to discover underlying auditory event clusters. We then train a neural network to predict the auditory events and use the prediction errors as intrinsic rewards to guide RL exploration. Experimental results on Atari games show that our new intrinsic motivation significantly outperforms several state-of-the-art baselines. We further visualize our noisy agents' behavior in a physics environment and demonstrate that our newly designed intrinsic reward leads to the emergence of physical interaction behaviors (e.g. contact with objects).