Meta-Learning for Wrestling
We show that for the task of simulated robot wrestling, a meta-learning agent can learn to quickly defeat a stronger non-meta-learning agent.
Maruan Al-Shedivat
Meta-Learning for Wrestling
We show that for the task of simulated robot wrestling, a meta-learning agent can learn to quickly defeat a stronger non-meta-learning agent.
Learning to Model Other Minds
We’re releasing an algorithm which accounts for the fact that other agents are learning too, and discovers self-interested yet collaborative strategies like tit-for-tat in the iterated prisoner’s dilemma. This algorithm, Learning with Opponent-Learning Awareness (LOLA), is a small step towards agents that model other minds.
LOLA, a collaboration
Learning to Model Other Minds
We’re releasing an algorithm which accounts for the fact that other agents are learning too, and discovers self-interested yet collaborative strategies like tit-for-tat in the iterated prisoner’s dilemma. This algorithm, Learning with Opponent-Learning Awareness (LOLA), is a small step towards agents that model other minds.
LOLA, a collaboration