Login / Signup

Simultaneously Learning Vision and Feature-Based Control Policies for Real-World Ball-In-A-Cup.

Devin SchwabJost Tobias SpringenbergMurilo Fernandes MartinsMichael NeunertThomas LampeAbbas AbdolmalekiTim HertweckRoland HafnerFrancesco NoriMartin A. Riedmiller
Published in: Robotics: Science and Systems (2019)
Keyphrases
  • decision making
  • real world
  • data mining
  • learning algorithm
  • real time
  • prior knowledge
  • control policies
  • neural network
  • reinforcement learning
  • supervised learning
  • markov chain
  • conditional random fields