On Simple Reactive Neural Networks for Behaviour-Based Reinforcement Learning
Ameya Pore,Gerardo Aragon-Camarasa,Ameya Pore,Gerardo Aragon-Camarasa
We present a behaviour-based reinforcement learning approach, inspired by Brook's subsumption architecture, in which simple fully connected networks are trained as reactive behaviours. Our working assumption is that a pick and place robotic task can be simplified by leveraging domain knowledge of a robotics developer to decompose and train reactive behaviours; namely, approach, grasp, and retract....
