1. 1 ADVANTAGE UPDATING
  2. 2 RESIDUAL GRADIENT ALGORITHMS
  3. 3 THE SIMULATION
    1. 3.1 GAME DEFINITION
    2. 3.2 THE BELLMAN RESIDUAL AND UPDATE EQUATIONS
  4. 4 RESULTS
    1. 4.1 RESIDUAL GRADIENT ADVANTAGE UPDATING RESULTS
    2. 4.2 COMPARATIVE RESULTS
      1. 4.2.1 Experiment Set 1
      2. 4.2.2 Experiment Set 2
  5. 5 Conclusion
      1. Acknowledgments
      2. References