Online Learning

Lamarckian Evolution of Simulated Modular Robots

We study evolutionary robot systems where not only the robot brains but also the robot bodies are evolvable. Such systems need to include a learning period right after ‘birth' to acquire a controller that fits the newly created body. In this paper we …

Revolve: A Versatile Simulator for Online Robot Evolution

Developing robotic systems that can evolve in real-time and real-space is a long term objective with technological as well as algorithmic milestones on the road. Technological prerequisites include advanced 3D-printing, automated assembly, and robust …

Morphological Attractors in Darwinian and Lamarckian Evolutionary Robot Systems

Morphological evolution in a robotic system produces novel robot bodies after each reproduction event. This implies the necessity for life-time learning so that newborn robots can acquire a controller that fits their body. Thus, we obtain a system …

Improving RL Power for On-Line Evolution of Gaits in Modular Robots

This paper addresses the problem of on-line gait learning in modular robots whose shape is not known in advance. The best algorithm for this problem known to us is a reinforcement learning method, called RL PoWER. In this study we revisit the …