• Research DeepMind’s latest research at ICLR 2022
• Impact MuZero’s first step from research into the real world
• Research On the Expressivity of Markov Reward
• Research Generally capable agents emerge from open-ended play
• Research Using Unity to Help Solve Intelligence
• Research Fast reinforcement learning through the composition of behaviours
• Research A new model and dataset for long-range memory
• Company From unlikely start-up to major scientific organisation: Entering our tenth year at DeepMind
• Company Strengthening the AI community
• Research AlphaStar: Grandmaster level in StarCraft II using multi-agent reinforcement learning