Login / Signup
A Narration-based Reward Shaping Approach using Grounded Natural Language Commands.
Nicholas R. Waytowich
Sean L. Barton
Vernon Lawhern
Garrett Warnell
Published in:
CoRR (2019)
Keyphrases
</>
natural language
reward shaping
reinforcement learning
complex domains
reinforcement learning algorithms
knowledge representation
state space
neural network
machine learning
dialogue system
reward function
mobile robot