Improving the Performance of Backward Chained Behavior Trees that use Reinforcement Learning.

Mart Kartasev Justin Saler Petter Ögren

Published in: IROS (2023)

Keyphrases

reinforcement learning
function approximation
decision trees
machine learning
temporal difference
bi directional
information systems
website
dynamic programming
multi agent reinforcement learning
learning process
human behavior
model free
behavior analysis
autonomous learning