← Search

Christopher Lu

2 accepted papers

2022

Model-Free Opponent Shaping

ICML 2022spotlight

In general-sum games the interaction of self-interested learning agents commonly leads to collectively worst-case outcomes, such as defect-defect in the iterated prisoner’s dilemma (IPD). To overcome this, some methods, such as Learning with Opponent-Learning Awareness (LOLA), directly shape the lea…

2019

Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity

NeurIPS 2019spotlight

Contemporary sensorimotor learning approaches typically start with an existing complex agent (e.g., a robotic arm), which they learn to control. In contrast, this paper investigates a modular co-evolution strategy: a collection of primitive agents learns to dynamically self-assemble into composite b…