Intrinsically Motivated Evolutionary Search for Vision-Based Reinforcement Learning

By Giuseppe Cuccu, Matthew D. Luciw, J. Urgen Schmidhuber, Faustino J. Gomez. 2011

18 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.

Citations in the corpus

Deep learning in neural networks: An overview (2014, background): “The compact codes (instead of the high-dimensional raw data) can be fed into an RL machine, whose job thus may become much easier (Legenstein et al., 2010; Cuccu et al., 2011), just like SL may profit from UL, e.”
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.,”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “2) [42] used as sensory preprocessors to create less redundant sensory codes [118, 138, 142, 46].”
Evolving deep unsupervised convolutional networks for vision-based reinforcement learning (2014, methodology): “A better approach might be to interleave the compressor evolution with controller evolution so that the compressor is trained continually using images generated by the controller as they become more and more proﬁcient in the task as in [3].”
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 "…”
Evolving large-scale neural networks for vision-based reinforcement learning (2013, methodology): “The idea of modifying an existing RL benchmark to use visual inputs dates back to the adaptive “broom balancer” of Tolat and Widrow [15], and more recently the vision-based mountain car in [1].”
Online Evolution of Deep Convolutional Network for Vision-Based Reinforcement Learning (2014, methodology): “In this paper, the feature learning and control learning are interleaved as in [3].”