Adapting Behaviour Via Intrinsic Reward: A Survey And Empirical Study

Abstract

Learning about many things can provide numerous benefits to a reinforcement learning system. For example, learning many auxiliary value functions, in addition to optimizing the environmental reward, appears to improve both exploration and representation learning. The question we tackle in this paper is how to sculpt the stream of experience---how to adapt the learning system's behavior---to optimize the learning of a collection of value functions. A simple answer is to compute an intrinsic reward based on the statistics of each auxiliary learner, and use reinforcement learning to maximize that intrinsic reward. Unfortunately, implementing this simple idea has proven difficult, and thus has been the focus of decades of study. It remains unclear which of the many possible measures of learning would work well in a parallel learning setting where environmental reward is extremely sparse or absent. In this paper, we investigate and compare different intrinsic reward mechanisms in a new band

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylinke2019adapting

Related papers

• What Can Learned Intrinsic Rewards Capture? (2019)0.00
• Rlexplore: Accelerating Research In Intrinsically-motivated Reinforcement Learning (2024)5.33
• On Learning Intrinsic Rewards For Policy Gradient Methods (2018)0.00
• Coordinated Exploration Via Intrinsic Rewards For Multi-agent Reinforcement Learning (2019)0.00
• A Survey On Intrinsic Motivation In Reinforcement Learning (2019)0.00
• Self-supervised Exploration Via Temporal Inconsistency In Reinforcement Learning (2022)3.58
• Redeeming Intrinsic Rewards Via Constrained Optimization (2022)0.00
• The Impact Of Intrinsic Rewards On Exploration In Reinforcement Learning (2025)0.00