Login / Signup
Continual Reinforcement Learning with Multi-Timescale Replay.
Christos Kaplanis
Claudia Clopath
Murray Shanahan
Published in:
CoRR (2020)
Keyphrases
</>
reinforcement learning
function approximation
state space
optimal policy
real world
learning algorithm
machine learning
multiscale
temporal difference
reinforcement learning algorithms
partially observable