Adding negative momentum to mirror descent, FTRL, and regret matching accelerates convergence in constrained zero-sum games, and the new MoCFR+ variant reports lower exploitability than CFR+ across multiple games.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Rapid Learning in Constrained Minimax Games with Negative Momentum
Adding negative momentum to mirror descent, FTRL, and regret matching accelerates convergence in constrained zero-sum games, and the new MoCFR+ variant reports lower exploitability than CFR+ across multiple games.