1. REINFORCEMENT LEARNING IN CONTINUOUS TIME:
2. ADVANTAGE UPDATING
3. ABSTRACT
4. REINFORCEMENT LEARNING
5. Q-LEARNING
6. ADVANTAGE UPDATING
   1. The Advantage Updating Algorithm
7. LINEAR QUADRATIC REGULATOR
8. SIMULATION RESULTS
9. CONCLUSION
10. ACKNOWLEDGMENTS
11. REFERENCES
12. APPENDIX: LQR CONSTANTS