Login / Signup

Learning to Parse Natural Language to Grounded Reward Functions with Weak Supervision.

Edward C. WilliamsNakul GopalanMina RheeStefanie Tellex
Published in: ICRA (2018)
Keyphrases
  • natural language
  • learning algorithm
  • learning process
  • reinforcement learning
  • prior knowledge
  • supervised learning
  • objective function
  • natural language processing
  • statistical model
  • dynamical systems
  • reward function