Exploring the T-Maze: Evolving Learning-Like Robot Behaviors Using CTRNNs

Abstract. This paper explores the capabilities of continuous time recurrent neural networks (CTRNNs) to display reinforcement learning-like abilities on a set of T-Maze and double T-Maze navigation tasks, where the robot has to locate and “remember” the position of a reward-zone. The “learning” comes about without modifications of synapse strengths, but simply from internal network dynamics, as proposed by [12]. Neural controllers are evolved in simulation and in the simple case evaluated on a real robot. The evolved controllers are analyzed and the results obtained are discussed.

• Type: Conference
• Year: 2003
• Where: EVOW
• Authors: Jesper Blynel, Dario Floreano
• Keywords: Artificial Intelligence, EVOW 2003, Recurrent Neural Networks, Reinforcement Learning-like Abilities, T-Maze Navigation Tasks