Christian A Schroeder De Witt

game theory (2) deep reinforcement learning (1) multi-agent reinforcement learning (1) multi-task learning (1) policy optimization (1) markov decision process (1) value function (1) multi-agent learning (1) policy improvement (1) policy training (1) counterfactual reasoning (1) markov game (1) zero-shot coordination (1) opponent shaping (1) minimum entropy coupling (1) trust region optimization (1) maximum entropy reinforcement learning (1) entity factorization (1) cooperative ai (1) belief learning (1)