Regularized Policy Iteration.
Amir Massoud FarahmandMohammad GhavamzadehCsaba SzepesváriShie MannorPublished in: NIPS (2008)
Keyphrases
- policy iteration
- least squares
- markov decision processes
- model free
- sample path
- fixed point
- reinforcement learning
- optimal policy
- average reward
- policy evaluation
- finite state
- infinite horizon
- markov decision problems
- markov decision process
- optimal control
- linear programming
- convergence rate
- temporal difference
- dynamic programming
- state space
- long run
- neural network
- average cost
- multistage
- multi agent
- image sequences