The Complexity of Interior Point Methods for Solving Discounted Turn-Based Stochastic Games.
Thomas Dueholm HansenRasmus Ibsen-JensenPublished in: CiE (2013)
Keyphrases
- stochastic games
- interior point methods
- markov decision processes
- quadratic programming
- average reward
- convex optimization
- solving problems
- infinite horizon
- nash equilibria
- primal dual
- linear programming
- optimal policy
- semidefinite programming
- linear program
- average cost
- decision problems
- nash equilibrium
- dynamic programming
- reinforcement learning algorithms
- long run
- worst case
- computational complexity
- multi agent
- computationally intensive
- finite number
- single agent
- incomplete information
- learning automata
- combinatorial optimization
- learning agent