Improved and Generalized Upper Bounds on the Complexity of Policy Iteration.
Bruno ScherrerPublished in: CoRR (2013)
Keyphrases
- upper bound
- policy iteration
- markov decision processes
- worst case
- lower bound
- model free
- reinforcement learning
- optimal policy
- decision problems
- fixed point
- finite state
- infinite horizon
- temporal difference
- sample path
- neural network
- least squares
- markov chain
- cost function
- convergence rate
- objective function
- average reward