Neuro-evolutionary Frameworks for Generalized Learning Agents
This addresses the problem of inefficient and non-generalizable learning in AI systems, but it is incremental as it builds on existing methods without presenting new empirical results.
The paper tackles the poor sample efficiency and limited generalization of deep learning by proposing neuro-evolutionary frameworks that combine deep learning with evolutionary algorithms to enable automated acquisition of behaviors and priors for generalized, continual learning with minimal environmental interaction.
The recent successes of deep learning and deep reinforcement learning have firmly established their statuses as state-of-the-art artificial learning techniques. However, longstanding drawbacks of these approaches, such as their poor sample efficiencies and limited generalization capabilities point to a need for re-thinking the way such systems are designed and deployed. In this paper, we emphasize how the use of these learning systems, in conjunction with a specific variation of evolutionary algorithms could lead to the emergence of unique characteristics such as the automated acquisition of a variety of desirable behaviors and useful sets of behavior priors. This could pave the way for learning to occur in a generalized and continual manner, with minimal interactions with the environment. We discuss the anticipated improvements from such neuro-evolutionary frameworks, along with the associated challenges, as well as its potential for application to a number of research areas.