C
search
search
reviewers
reviewers
feeds
feeds
assignments
assignments
settings
logout
Designing Curriculum for Deep Reinforcement Learning in StarCraft II.
Daniel Hao
Penny Sweetser
Matthew Aitchison
Published in:
Australasian Conference on Artificial Intelligence (2020)
Keyphrases
</>
reinforcement learning
function approximation
markov decision processes
multi agent
supervised learning
optimal policy
high school
temporal difference learning
action selection
model free
professional development
optimal control
state space
dynamic programming
temporal difference
cooperative
transition model