Scaling Opponent Shaping to High Dimensional Games
CoRR(2023)
摘要
In multi-agent settings with mixed incentives, methods developed for zero-sum
games have been shown to lead to detrimental outcomes. To address this issue,
opponent shaping (OS) methods explicitly learn to influence the learning
dynamics of co-players and empirically lead to improved individual and
collective outcomes. However, OS methods have only been evaluated in
low-dimensional environments due to the challenges associated with estimating
higher-order derivatives or scaling model-free meta-learning. Alternative
methods that scale to more complex settings either converge to undesirable
solutions or rely on unrealistic assumptions about the environment or
co-players. In this paper, we successfully scale an OS-based approach to
general-sum games with temporally-extended actions and long-time horizons for
the first time. After analysing the representations of the meta-state and
history used by previous algorithms, we propose a simplified version called
Shaper. We show empirically that Shaper leads to improved individual and
collective outcomes in a range of challenging settings from literature. We
further formalize a technique previously implicit in the literature, and
analyse its contribution to opponent shaping. We show empirically that this
technique is helpful for the functioning of prior methods in certain
environments. Lastly, we show that previous environments, such as the CoinGame,
are inadequate for analysing temporally-extended general-sum interactions.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要