Assessing Evolutionary Terrain Generation Methods for Curriculum Reinforcement Learning

no code implementations • 29 Mar 2022 • David Howard, Josh Kannemeyer, Davide Dolcetti, Humphrey Munn, Nicole Robinson

To allow direct comparison between both direct and indirect representations, we assess the impact of a range of representation-agnostic MAP-Elites feature descriptors that compute metrics directly from the generated terrain meshes.

reinforcement-learning Reinforcement Learning (RL)