János Kramár

Negotiation and honesty in artificial intelligence methods for the board game of Diplomacy

2022 · Nature Communications

The success of human civilization is rooted in our ability to cooperate by communicating and making joint plans. We study how artificial agents may use communication to better cooperate in Diplomacy, a long-standing AI challenge. …

Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations

2016 · PolyPublie (École Polytechnique de Montréal)

We propose zoneout, a novel method for regularizing RNNs. At each timestep, zoneout stochastically forces some hidden units to maintain their previous values. Like dropout, zoneout uses random noise to train a pseudo-ensemble, improving generalization. …