Incremental Evolution of Complex General Behavior

By Faustino J. Gomez, Risto Miikkulainen. 1997

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

Evolving Deep Neural Networks (2017, methodology): “Other approaches such as SANE, ESP, and CoSyNE evolve partial neural networks and combine them into fully functional networks [12, 14, 37].”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “In principle, this can be done through incremental NN evolution [70], hierarchical NN evolution [306, 285], hierarchical Policy Gradient algorithms [63], or asymptotically optimal ways of algorithmic transfer learning [238].”
One Big Net For Everything (2018, methodology): “…of ONE are trained in a series of trials through a black box optimization method in Step 3 of Algorithm 1, e.g., through incremental neuroevolution [17], hierarchical neuroevolution [100, 93], hierarchical policy gradient algorithms [13], or asymptotically optimal ways of algorithmic transfer…”
Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions (2019, background): “This kind of incremental curriculum is intuitive and variants of it appear in the literature when a task is too hard to learn directly [40, 67–70].”
The road to everywhere : Evolution, complexity and progress in natural and artificial systems (2008, methodology): “the players for the game of tag evolved by Reynolds, [149], or Gomez and Miikkulainen’s ESP method for the cooperative coevolution of neurons in a neural network [66]).”
Discovering Gated Recurrent Neural Network Architectures (2018, background): “Long Short Term Memory (LSTM) (Hochreiter and Schmidhuber (1997a)) successfully overcomes these limitations of RNNs.”
Evolving Deep LSTM-based Memory Networks using an Information Maximization Objective (2016, background): “This problem can be broken down using incremental evolution [9] (without the need for domain knowledge).”
Evolving Soccer Keepaway Players Through Task Decomposition (2005, methodology): “Since delta-coding is particularly well suited to helping populations adjust to sudden changes in their training environment (Gomez and Miikkulainen, 1997), it is an excellent way to seed a new population from the results of an earlier layer.”
Accelerated Neural Evolution through Cooperatively Coevolved Synapses (2008, background): “Our previous method, Enforced SubPopulations, is a particularly effective neuroevolution algorithm that has been a applied successfully to many domains (Perez- Bergquist, 2001; Lubberts and Miikkulainen, 2001; Greer et al., 2002; Whiteson et al., 2003; Bryant and Miikkulainen, 2003; Gomez et al., 20”
Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes (2008, methodology): “To improve our previous implementations of these in gredients (Section 3), we will (1) study better adaptive compressors, in particula r, recent, novel RNNs [94] and other general but practically feasible methods for maki ng predictions [75]; (2) investigate under which conditions learning progress ”
Evolving Neural Networks through Augmenting Topologies (2002, background): “A parallel can be drawn between structure evolution in NEAT and incremental evolution (Gomez and Miikkulainen, 1997; Wieland, 1991).”
Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions (2020, background): “Interestingly, much research effort is spent attempting to design or learn single-path curricula to help an agent learn a complex task (Bengio et al., 2009; Gomez & Miikkulainen, 1997; Heess et al., 2017; Justesen et al., 2018; Karpathy & Van De Panne, 2012).”
Evolving Memory Cell Structures for Sequence Learning (2009, background): “We start with evolving cells capable of learning simple versions of the problems; once these problems can be learnt satisfactorily, we increase the complexity of the problem, a practice known as incremental evolution [5].”
Autonomous Evolution of Topographic Regularities in Artificial Neural Networks (2010, background): “Inearly NE research, humans dictated the topology and encoding of evolved ANNs (Beer & Gallagher, 1992; Gomez & Miikkulainen, 1997; Kampfner & Conrad, 1983; Montana & Davis, 1989; Srinivas & Paranaik, 1991; Whitley, 1995; Wieland, 1991).”