Non-Stationary Approximate Modified Policy Iteration.
Boris LesnerBruno ScherrerPublished in: ICML (2015)
Keyphrases
- non stationary
- policy iteration
- policy evaluation
- markov decision processes
- factored mdps
- approximate policy iteration
- least squares
- model free
- reinforcement learning
- optimal policy
- sample path
- fixed point
- temporal difference
- markov decision process
- finite state
- adaptive algorithms
- infinite horizon
- function approximation
- monte carlo
- linear programming
- markov decision problems
- state space
- average cost
- average reward
- empirical mode decomposition
- variance reduction
- dynamic programming
- optimal control
- optimal solution
- video sequences