Knowledge is reward: Learning optimal exploration by predictive reward cashing

Abstract

There is a strong link between the general concept of intelligence and the ability to collect and use information. The theory of Bayes-adaptive exploration offers an attractive optimality framework for training machines to perform complex information gathering tasks. However, the computational complexity of the resulting optimal control problem has limited the diffusion of the theory to mainstream deep AI research. In this paper we exploit the inherent mathematical structure of Bayes-adaptive problems in order to dramatically simplify the problem by making the reward structure denser while simultaneously decoupling the learning of exploitation and exploration policies. The key to this simplification comes from the novel concept of cross-value (i.e. the value of being in an environment while acting optimally according to another), which we use to quantify the value of currently available information. This results in a new denser reward structure that "cashes in" all future rewards that can be predicted from the current information state. In a set of experiments we show that the approach makes it possible to learn challenging information gathering tasks without the use of shaping and heuristic bonuses in situations where the standard RL algorithms fail.

References in corpus (11)

• A Conceptual Introduction to Hamiltonian Monte Carlo
• RL${}^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• Learning to reinforcement learn
• #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
• Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
• Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search
• Curiosity-driven Exploration for Mapless Navigation with Deep Reinforcement Learning
• Bootstrapped Thompson Sampling and Deep Exploration
• Curiosity-Driven Experience Prioritization via Density Estimation
• Offline Meta Learning of Exploration
• A learning gap between neuroscience and reinforcement learning