Login / Signup
A Simple Approach for State-Action Abstraction using a Learned MDP Homomorphism.
Augustine N. Mavor-Parker
Andrea Banino
Lewis D. Griffin
Caswell Barry
Published in:
CoRR (2022)
Keyphrases
</>
state action
markov decision process
average reward
reinforcement learning
markov decision processes
action space
evaluation function
stochastic games
neural network
state space
utility function
linear program
long run