2 papers
cs.LG2026
Optimistic Policy Regularization
Mai Pham, Vikrant Vaze, Peter Chin
Deep reinforcement learning agents frequently suffer from premature convergence, where early entropy collapse causes the policy to discard exploratory behaviors before discovering…
cs.GT2025
Advancing Differentiable Economics: A Neural Network Framework for Revenue-Maximizing Combinatorial Auction Mechanisms
Mai Pham, Vikrant Vaze, Peter Chin
Differentiable economics, which uses neural networks as function approximators and gradient-based optimization in automated mechanism design (AMD), marked a significant breakthroug…