Adaptive confidence and adaptive curiosity

By J. Urgen Schmidhuber. 1991

How researchers see this paper

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

In Reinforcement Learning

Citations in the corpus

Learning Parameterized Skills (2012, background): “, [60, 61]), where he posits that intrinsically motivated agents are interested in learnable but yet unknown regularities, but bored by predictable or inherently unpredictable events.”
Self-Imitation Learning (2018, methodology): “Many existing methods use some notion of curiosity or uncertainty as a signal for exploration (Schmidhuber, 1991; Strehl & Littman, 2008).”
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation (2018, background): “Curiosity or uncertainty has been used as a signal for exploration [33, 35, 23, 29].”
Exploration Bonuses and Dual Control (1996, methodology): “The agent could use these uncertainties in an analogue of the systems of Schmidhuber (1991) or Thrun & Möller (1992).”
Using MDP Characteristics to Guide Exploration in Reinforcement Learning (2003, background): “Error-based exploration [10] prefers actions leading to states whose value changed most in past updates.”
Intrinsically Motivated Reinforcement Learning: An Evolutionary Perspective (2010, methodology): “special types of reward functions and then employing standard RL learning procedures, an approach first suggested by Schmidhuber [32] as a way to create an artificial analog of curiosity.”
Intrinsic Motivation and Reinforcement Learning (2013, methodology): “Schmidhuber (1991a, 1991b, 1997, 1999) introduced methods for implementing forms of curiosity using RL algorithms, and Sutton’s (1991) “exploration bonus” is a form of intrinsic reward.”
Learning to Act Using Real-Time Dynamic Programming (1995, background): “Kaelbling [34], Lin [46], Moore [53], Schmidhuber [61], Sutton [67], Thrun [77], and Thrun and Moller [76] discuss these and other possibilities.”
ELLA: Exploration through Learned Language Abstraction (2021, methodology): “Another technique for improving sample efficiency is through intrinsic motivation (Schmidhuber, 1991; Pathak et al., 2017; Burda et al., 2019).”