Machine Learning II course

• Robotics
  • Computer Sim Teaches Itself To Walk Upright (virtual robots (of different shapes) learning to walk, through stochastic optimization (CMA-ES)), by Utrecht University
  • In the same spirit: Evolved Virtual Creatures, by Karl Sims.
  • Towards Learning Robot Table Tennis, by Jan Peters' lab
  • Learning Motor Primitives for Robotics (bilboquet), by Jan Peters' lab again
  • Robot Learns to Flip Pancakes, by Dr. Petar Kormushev, Advanced Robotics dept., Italian Institute of Technology (IIT)
  • Robots that can adapt like animals (a six-legged robot adapts to keep walking after two of its legs are broken), by Inria / Université Pierre et Marie Curie (Jean-Baptiste Mouret) [Nature article]
  • Starfish Self Modeling Robot, by Cornell Creative Machines lab
  • Quadrocopter Ball Juggling, by ETH Zurich
  • Introducing Spot (a walking dog robot), by Boston Dynamics
  • Learning to Swing-Up and Balance from Scratch, by Martin Riedmiller at Uni Freiburg
  
  
• Computer games
  • Human-level control through deep reinforcement learning to play various Atari games, by Volodymyr Mnih et al.
  • Action-Conditional Video Prediction using Deep Networks in Atari Games, by University of Michigan
  • Using reinforcement learning to train Ms. Pac-Man
  • Reinforcement learning agent plays Ms. Pac-Man, by Szita & Lörincz
  • Reinforcement learning agent plays Tetris, by Szita and Lörincz again
  • Q-Learning Snake (finishing the game!)
  • Reinforcement Learning Super Mario