Intrinsic Motivation For Reinforcement Learning Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Active learning of inverse models with intrinsically motivated goal exploration in robots (2013, neutral): “In traditional active learning methods and especially knowledge-based intrinsically motivated exploration [104,16,58,39,42], the system is typically designed to select actions to perform inside a set of values inside an already known interval (for instance, the range of angles that can be taken by…”
What is Intrinsic Motivation? A Typology of Computational Approaches (2007, background): “…cant number of cognitive architectures including particular models of intrinsic motivation have already been developed in the literature (e.g., Barto and Simsek, 2005; Bonarini et al., 2006; Huang and Weng, 2002; Kaplan and Oudeyer, 2003; Marshall et al., 2004; Merrick and Maher, 2008;…”
An intrinsic reward mechanism for efficient exploration (2006, background): “This formulation not only reveals how our algorithm approximates the solution to a well-defined optimization problem but also provides a basis for directions of future development.”
Emerging social awareness: Exploring intrinsic motivation in multiagent learning (2011, background): “include the hierarchical acquisition of skills using intrinsically motivated reinforcement learning [5]-[7], the acquisition of a visual-attention system from motivation variables [8], and others [3], [4], [9], [10].”