Login / Signup
GLDAP: Global Dynamic Action Persistence Adaptation for Deep Reinforcement Learning.
Junbo Tong
Daming Shi
Yi Liu
Wenhui Fan
Published in:
ACM Trans. Auton. Adapt. Syst. (2023)
Keyphrases
</>
reinforcement learning
dynamic environments
function approximation
action selection
machine learning
state space
learning process
policy search
partially observable domains
multi agent
markov decision processes
temporal difference
adaptation process