Login / Signup

Q-learning with Long-term Action-space Shaping to Model Complex Behavior for Autonomous Lane Changes.

Gabriel KalweitMaria HügleMoritz WerlingJoschka Boedecker
Published in: IROS (2021)
Keyphrases
  • long term
  • state space
  • probabilistic model
  • objective function
  • hidden markov models
  • dynamic environments
  • markov models