Timon Willi

multi-agent learning (2) opponent shaping (2) multi-agent reinforcement learning (1) reinforcement learning (1) game theory (1) function approximation (1) class imbalance (1) gradient descent (1) adversarial attack (1) gpu acceleration (1) unsupervised environment design (1) classifier selection (1) environment simulation (1) general-sum game (1) parallel training (1) adversarial evaluation (1) balanced accuracy (1) consistent learning (1) prosocial solution (1) starcraft multi-agent challenge (1)