Reinforcement Learning Can Be More Efficient with Multiple Rewards.

Christoph Dann Yishay Mansour Mehryar Mohri

Published in: ICML (2023)

Keyphrases

reinforcement learning
markov decision processes
learning algorithm
function approximation
state space
search algorithm
lightweight
temporal difference
data mining
computationally expensive
optimal control
multiple objects
temporal difference learning
robotic control