Multi-Player Residual Advantage Learning With General Function Approximation

  title={Multi-Player Residual Advantage Learning With General Function Approximation},
  author={Mance E. Harmon},
A new algorithm, advantage learning, is presented that improves on advantage updating by requiring that a single function be learned rather than two. Furthermore, advantage learning requires only a single type of update, the learning update, while advantage updating requires two different types of updates, a learning update and a normilization update. The reinforcement learning system uses the residual form of advantage learning. An application of reinforcement learning to a Markov game is… CONTINUE READING
Highly Cited
This paper has 53 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 31 extracted citations

53 Citations

Citations per Year
Semantic Scholar estimates that this publication has 53 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 13 references

Advantage updating Wright-Patterson Air Force Base, OH

  • L. C. Baird
  • (Wright Laboratory Technical Report WL-TR-93-1146…
  • 1993
Highly Influential
6 Excerpts

Associative reinforcement learning for optimal control

  • P. J. Milli ngton
  • Unpublished master's thesis, Massachusetts…
  • 1991
2 Excerpts

Similar Papers

Loading similar papers…