World Discovery Models
This addresses the challenge of enabling AI systems to autonomously explore and learn from their environments, which is incremental as it builds on existing information-seeking methods.
The paper tackles the problem of building an AI agent capable of discovering its world by seeking novelty and refining understanding from partial, noisy observations, introducing NDIGO, which outperforms state-of-the-art information-seeking methods in 2-D navigation tasks, particularly in noisy conditions.
As humans we are driven by a strong desire for seeking novelty in our world. Also upon observing a novel pattern we are capable of refining our understanding of the world based on the new information---humans can discover their world. The outstanding ability of the human mind for discovery has led to many breakthroughs in science, art and technology. Here we investigate the possibility of building an agent capable of discovering its world using the modern AI technology. In particular we introduce NDIGO, Neural Differential Information Gain Optimisation, a self-supervised discovery model that aims at seeking new information to construct a global view of its world from partial and noisy observations. Our experiments on some controlled 2-D navigation tasks show that NDIGO outperforms state-of-the-art information-seeking methods in terms of the quality of the learned representation. The improvement in performance is particularly significant in the presence of white or structured noise where other information-seeking methods follow the noise instead of discovering their world.