Keyphrases
- simplex method
- strongly polynomial
- markov decision processes
- linear programming
- linear program
- dynamic programming
- policy iteration
- stationary policies
- finite state
- state space
- optimal policy
- reinforcement learning
- primal dual
- optimal solution
- transition matrices
- interior point methods
- np hard
- decision theoretic planning
- column generation
- markov decision problems
- average reward
- integer programming
- average cost
- objective function
- markov decision process
- partially observable
- reward function
- infinite horizon
- minimum cost flow
- convergence rate
- multi objective
- knapsack problem
- sufficient conditions