Login / Signup
Average case analysis of the classical algorithm for Markov decision processes with Büchi objectives.
Krishnendu Chatterjee
Manas Joglekar
Nisarg Shah
Published in:
Theor. Comput. Sci. (2015)
Keyphrases
</>
average case
markov decision processes
worst case
objective function
optimal solution
dynamic programming
model based reinforcement learning
reinforcement learning
policy iteration
average reward
worst case analysis
machine learning
np hard
linear programming
theoretical analysis
planning under uncertainty