Artificial curiosity with planning for autonomous perceptual and cognitive development

By Matthew D. Luciw, Vincent Graziano, Mark B. Ring, J. Urgen Schmidhuber. 2011

33 citations recorded by the source corpus.

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Active learning of inverse models with intrinsically motivated goal exploration in robots (2013, positive): “This is the reason why new active learning heuristics have been proposed in developmental robotics, such as those based on the psychological concept of intrinsic motivations [54, 46, 55] which relate to mechanisms that drive a learning agent to perform different activities for their own sake, withou”
PowerPlay: Training an Increasingly General Problem Solver by Continually Searching for the Simplest Still Unsolvable Problem (2011, neutral): “One should analyze theoretically and experimentally under which conditions the creation of selfgenerated tasks can accelerate the solution to externally generated tasks – see (Schmidhuber, 1991a, 1999, 2002; Storck et al., 1995; Cuccu et al., 2011; Luciw et al., 2011; Schaul et al., 2011; Yi et al.,”
Intrinsically Motivated Learning in Natural and Artificial Systems (2013, methodology): “2008) or other devices that compute action sequences (Cuccu et al. 2011; Luciw et al. 2011; Schaul et al. 2011b)? Or a policy gradient method (Rückstieß et al.”
The strategic student approach for life-long exploration and learning (2012, background): “A second family of approaches have considered internal mechanisms of maturation, which control the evolution of the complexity of percepts and actions by progressively increasing the number or spatio-temporal resolution of motor channels [4], [5] or sensori channels [5]–[7].”
Arousal regulation and affective adaptation to human responsiveness by a robot that explores and learns a novel environment (2014, background): “Typical architectures modeling curiosity aimed at guiding the exploration of a developing robot often focus on speciﬁc task learning problem (Kaplan and Oudeyer, 2005; Luciw et al., 2011) and do not take advantage of the potential availability of humans.”
Curiosity driven reinforcement learning for motion planning on humanoids (2014, background): “Luciw et al. (2011) built a curious planner with a high-dimensional sensory space.”
Maximizing Fun by Creating Data with Easily Reducible Subjective Complexity (2013, background): “More recently implemented variants deal with applications to vision-based reinforcement learning/evolutionary search (Cuccu et al. 2011; Luciw et al. 2011), active learning of currently easily learnable functions (Ngo et al. 2011), blackbox optimization (Schaul et al. 2011b), and detection of "…”