Average Case Analysis of the Classical Algorithm for Markov Decision Processes with Büchi Objectives
Krishnendu ChatterjeeManas JoglekarNisarg ShahPublished in: CoRR (2012)
Keyphrases
- average case
- markov decision processes
- dynamic programming
- worst case
- reinforcement learning
- theoretical analysis
- model based reinforcement learning
- learning algorithm
- uniform distribution
- finite state
- objective function
- state space
- optimal policy
- computational complexity
- policy iteration
- real time dynamic programming
- search space
- linear programming
- optimal solution
- action space