Dual Policy Iteration.
Wen SunGeoffrey J. GordonByron BootsJ. Andrew BagnellPublished in: CoRR (2018)
Keyphrases
- policy iteration
- markov decision processes
- model free
- fixed point
- optimal policy
- reinforcement learning
- sample path
- least squares
- temporal difference
- average reward
- policy evaluation
- markov decision process
- infinite horizon
- finite state
- convergence rate
- optimal control
- markov decision problems
- linear programming
- dynamic programming
- average cost
- neural network
- random variables
- optical flow
- function approximation
- monte carlo