Evolving Hierarchical Memory-Prediction Machines in Multi-Task Reinforcement Learning

no code implementations • 23 Jun 2021 • Stephen Kelly, Tatiana Voegerl, Wolfgang Banzhaf, Cedric Gondro

We use genetic programming to evolve highly-generalized agents capable of operating in six unique environments from the control literature, including OpenAI's entire Classic Control suite.

reinforcement-learning Reinforcement Learning (RL)