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