Regularized last-iterate solvers select the maximum-entropy Nash equilibrium while regret-averaging methods select lower-entropy faces on zero-sum Nash polytopes, verified on analytic testbeds and a 180-game ensemble.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
PPO with moderate entropy regularization and current-policy self-play outperforms Monte Carlo Q, SARSA, and Q-learning in a controlled self-play framework for the imperfect-information game Big 2.
citing papers explorer
-
Self-Play Reinforcement Learning under Imperfect Information in Big 2
PPO with moderate entropy regularization and current-policy self-play outperforms Monte Carlo Q, SARSA, and Q-learning in a controlled self-play framework for the imperfect-information game Big 2.