← Search

Kenneth O. Stanley

2 accepted papers

2021

Deep Innovation Protection: Confronting the Credit Assignment Problem in Training Heterogeneous Neural Architectures

AAAI 2021technical

Deep reinforcement learning approaches have shown impressive results in a variety of different domains, however, more complex heterogeneous architectures such as world models require the different neural components to be trained separately instead of end-to-end. While a simple genetic algorithm rece…

2019

Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity

ICLR 2019poster

The impressive lifelong learning in animal brains is primarily enabled by plastic changes in synaptic connectivity. Importantly, these changes are not passive, but are actively controlled by neuromodulation, which is itself under the control of the brain. The resulting self-modifying abilities of th…

Cited by 105SourcePDFScholar