Approximate Policy Iteration with a Policy Language Bias: Solving Relational Markov Decision Processes
Alan FernRobert GivanSung Wook YoonPublished in: CoRR (2011)
Keyphrases
- markov decision processes
- approximate policy iteration
- policy iteration
- markov decision problems
- markov games
- optimal policy
- transition matrices
- partially observable
- reinforcement learning
- state space
- markov decision process
- finite state
- infinite horizon
- average cost
- decision processes
- action space
- reinforcement learning algorithms
- finite horizon
- least squares
- fixed point
- dynamic programming
- decision theoretic
- reward function
- planning under uncertainty
- temporal difference
- linear programming
- average reward
- optimal control
- convergence rate
- queueing networks
- stochastic games
- step size
- multi agent