My research focuses on skill learning in robots and learning agents in general, and the development of intelligent systems that can act autonomously in dynamic, uncertain and unstructured environments. Towards this goal, we study different perceptual-motor learning tasks on various robotic platforms (humanoids, manipulators, and mobile robots) in simulations and real environments and use methods from robotics and machine learning, in particular, imitation, reinforcement, and deep learning. We combine data-driven approaches with model-based formulations by exploring the mathematical structure of intelligent systems acting in a complex environment in terms of geometry, optimal control, and probability theory. Since human capabilities are far beyond those of artificial systems, we try to gain further insights into intelligent systems from studies in human motor control, biomimetics, neuroscience, and psychology.

Current Research Topics:

  • Learning agents and intelligent systems
  • Reinforcement learning
  • Imitation learning
  • Mathematics for intelligent systems


DFG grant (2021-2024) jointly awarded with Jan Peters, Technical University of Darmstadt, Germany

Curriculum Learning with Hindsight Experience Replay for Sequential Object Manipulation Tasks

Binyamin Manela, Armin Biess, Neural Networks, 145, 2021

Evaluating Guided Policy Search for Human Handovers

Alap Kshirsagar, Guy Hoffman, Armin Biess, ICRA 2021/R-AL

Bias-Reduced Hindsight Experience Replay with Virtual Goal Prioritization

Binyamin Manela, Armin Biess, Neurocomputing, 451, 2021

Siemens Challenge: Learning a high-precision robotic assembly task using pose estimation from simulated depth images

Yuval Litvak, Armin Biess and Aharon Bar-Hillel