Rollout Sampling Approximate Policy Iteration
Christos DimitrakakisMichail G. LagoudakisPublished in: CoRR (2008)
Keyphrases
- approximate policy iteration
- reinforcement learning
- policy iteration
- markov decision problems
- policy search
- markov decision processes
- markov games
- temporal difference
- optimal policy
- reinforcement learning algorithms
- linear programming
- markov decision process
- state space
- function approximators
- dynamic programming
- multiagent reinforcement learning
- model free
- least squares
- function approximation
- decision theoretic
- control problems
- finite state
- monte carlo
- neural network
- queueing networks
- fixed point
- markov chain
- multi agent