Asynchronous policy evaluation and enforcement.
Matthew BurnsideAngelos D. KeromytisPublished in: CSAW (2008)
Keyphrases
- policy evaluation
- least squares
- reinforcement learning
- temporal difference
- monte carlo
- model free
- markov decision processes
- policy iteration
- variance reduction
- matrix inversion
- function approximation
- semi parametric
- evaluation function
- fixed point
- optimal policy
- linear programming
- linear regression
- partially observable markov decision processes
- decision making