Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning
This addresses the computational bottleneck of existing mutual information optimization methods for machine learning applications, particularly in reinforcement learning, though it is incremental as it builds on variational inference and deep learning techniques.
The paper tackles the problem of scalable optimization of mutual information, which is crucial for intrinsically-motivated reinforcement learning, by introducing a variational approach combined with deep learning, enabling empowerment-based reasoning directly from pixels to actions.
The mutual information is a core statistical quantity that has applications in all areas of machine learning, whether this is in training of density models over multiple data modalities, in maximising the efficiency of noisy transmission channels, or when learning behaviour policies for exploration by artificial agents. Most learning algorithms that involve optimisation of the mutual information rely on the Blahut-Arimoto algorithm --- an enumerative algorithm with exponential complexity that is not suitable for modern machine learning applications. This paper provides a new approach for scalable optimisation of the mutual information by merging techniques from variational inference and deep learning. We develop our approach by focusing on the problem of intrinsically-motivated learning, where the mutual information forms the definition of a well-known internal drive known as empowerment. Using a variational lower bound on the mutual information, combined with convolutional networks for handling visual input streams, we develop a stochastic optimisation algorithm that allows for scalable information maximisation and empowerment-based reasoning directly from pixels to actions.