Approximate Modified Policy Iteration
Bruno ScherrerVictor GabillonMohammad GhavamzadehMatthieu GeistPublished in: CoRR (2012)
Keyphrases
- policy iteration
- policy evaluation
- markov decision processes
- factored mdps
- approximate policy iteration
- least squares
- reinforcement learning
- model free
- optimal policy
- sample path
- fixed point
- markov decision process
- temporal difference
- finite state
- infinite horizon
- approximate value iteration
- markov decision problems
- average reward
- hybrid algorithms
- linear programming
- convergence rate
- monte carlo
- variance reduction
- optimal control
- discounted reward
- state space