Login / Signup

Maximum entropy inverse reinforcement learning in continuous state spaces with path integrals.

Navid AghasadeghiTimothy Bretl
Published in: IROS (2011)
Keyphrases
  • maximum entropy
  • inverse reinforcement learning
  • reward function
  • markov models
  • state space
  • random fields
  • reinforcement learning
  • conditional random fields
  • decision making
  • pairwise
  • prior knowledge
  • control policies