Active Learning for Autonomous Intelligent Agents: Exploration, Curiosity, and Interaction

Abstract

In this survey we present different approaches that allow an intelligent agent to explore autonomous its environment to gather information and learn multiple tasks. Different communities proposed different solutions, that are in many cases, similar and/or complementary. These solutions include active learning, exploration/exploitation, online-learning and social learning. The common aspect of all these approaches is that it is the agent to selects and decides what information to gather next. Applications for these approaches already include tutoring systems, autonomous grasping learning, navigation and mapping and human-robot interaction. We discuss how these approaches are related, explaining their similarities and their differences in terms of problem assumptions and metrics of success. We consider that such an integrated discussion will improve inter-disciplinary research and applications.

References in corpus (6)

• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
• Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots
• Near-optimal Nonmyopic Value of Information in Graphical Models
• Accelerating Reinforcement Learning through Implicit Imitation
• Selecting the State-Representation in Reinforcement Learning
• Multi-class Generalized Binary Search for Active Inverse Reinforcement Learning