Michael Everett

deep reinforcement learning (1) multi-agent reinforcement learning (1) reinforcement learning (1) adversarial robustness (1) policy optimization (1) average reward (1) formal guarantee (1) certified defense (1) deep q-network (1) multiagent reinforcement learning (1) equilibrium selection (1) worst-case deviation (1) formal robustness guarantee (1) long-term performance (1) farsighted objective (1) limiting policy (1)