Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees.

Gregory Dexter Kevin Bello Jean Honorio

Published in: NeurIPS (2021)

Keyphrases

inverse reinforcement learning
continuous state spaces
state space
reward function
preference elicitation
markov decision processes
reinforcement learning
continuous state
semi supervised
linear programming
dynamical systems
learning problems
state variables
initial state