Artificial curiosity based on discovering novel algorithmic predictability through coevolution

By J. Urgen Schmidhuber. 1999

How researchers see this paper

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

Citations in the corpus

Active learning of inverse models with intrinsically motivated goal exploration in robots (2013, positive): “First, algorithms achieving competence based exploration and allowing general computer programs to actively and adaptively self-generate abstract computational problems, or goals, of increasing complexity were studied in a theoretical computer science perspective [90–92].”
PowerPlay: Training an Increasingly General Problem Solver by Continually Searching for the Simplest Still Unsolvable Problem (2011, methodology): “This guaranteed robustness against forgetting previous sk ills also represents a difference to the most closely related previous work [37, 38].”
First Experiments with PowerPlay (2012, background): “Unlike our first implementations of curious / creative / playful agents from the 1990s [17, 29, 18] (cf.”
Intrinsically motivated action-outcome learning and goal-based action recall: a system-level bio-constrained computational model. (2013, background): “Interestingly, Schmidhuber (1991a, 1999) (see Schmidhuber, 2010, for a review) has later proposed that this mechanism might have difficulties if the predictor cannot learn to predict the consequences of some actions, in particular because the world is stochastic or because of the computational…”
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.”
Understanding the origin of information-seeking exploration in probabilistic objectives for control (2021, background): “…been studied in a vast number of fields ranging from machine learning and reinforcement learning (Kaelbling et al., 1998; Oudeyer & Kaplan, 2009; Schmidhuber, 1991, 1999, 2007; Sun et al., 2011; Thrun, 1992; Thrun & Möller, 1991), cognitive science and neuroscience (Cohen et al., 2007; Daw,…”