DNQ: Deep Nash Q-Network for Partially Observable n-Player Games
- Published
- Source
- arXiv
- Paper number
- 331
- Field
- Game Theory
- arXiv ID
- 2606.06480
Key points
- It trains bidding agents with a solver-in-the-loop equilibrium supervision framework.
- A shared critic predicts a pairwise payoff matrix or an N-player payoff tensor to improve training efficiency.
- The pairwise formulation greatly reduces compute cost compared with the exact N-player formulation.
- The exact method becomes computationally infeasible as the number of agents increases.
- It empirically shows the tradeoff between strategic fidelity and scalability.
Paper links
External research summaries. These are not HDATF publications or measured product results.