Login / Signup
Dynamic Regret of Adversarial Linear Mixture MDPs.
Long-Fei Li
Peng Zhao
Zhi-Hua Zhou
Published in:
NeurIPS (2023)
Keyphrases
</>
markov decision processes
dynamic environments
reinforcement learning
mixture model
closed form
multi agent
loss function
game theory
learning algorithm
support vector
multi agent systems
exponential family
regret bounds