Speeding up learning with dynamic environment shaping in evolutionary robotics
Abstract
Evolutionary Robotics is a promising approach to automatically build efficient controllers using stochastic optimization techniques. However, works in this area are often confronted to complex environments where even simple tasks cannot be achieved. In the scope of this paper, we propose an approach based on explicit problem decomposition and dynamic environment shaping to ease the learning task.
Domains
Artificial Intelligence [cs.AI]
Origin : Files produced by the author(s)
Loading...