Login / Signup
Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration.
Andrea Zanette
Alessandro Lazaric
Mykel J. Kochenderfer
Emma Brunskill
Published in:
NeurIPS (2020)
Keyphrases
</>
database
state space
computationally expensive
average reward
case study
multiscale
reinforcement learning
lightweight
long run
robot navigation