Evolving intrinsic motivations for altruistic behavior

Jane X. Wang, Edward Hughes, Chrisantha Fernando, Wojciech M. Czarnecki, Edgar A. Duenez-Guzman, Joel Z. Leibo

Abstract: Multi-agent cooperation is an important feature of the natural world. Many tasks involve individual incentives that are misaligned with the common good, yet a wide range of organisms from bacteria to insects and humans are able to overcome their differences and collaborate. Therefore, the emergence of cooperative behavior amongst self-interested individuals is an important question for the fields of multi-agent reinforcement learning (MARL) and evolutionary theory. Here, we study a particular class of multi-agent problems called intertemporal social dilemmas (ISDs), where the conflict between the individual and the group is particularly sharp. By combining MARL with appropriately structured natural selection, we demonstrate that individual inductive biases for cooperation can be learned in a model-free way. To achieve this, we introduce an innovative modular architecture for deep reinforcement learning agents which supports multi-level selection. We present results in two challenging environments, and interpret these in the context of cultural and ecological evolution.

Keywords: evolution, reinforcement learning, intrinsic reward, multi-agent, social dilemmas, cooperation

TL;DR: We introduce a biologically-inspired modular evolutionary algorithm in which deep RL agents learn to cooperate in a difficult multi-agent social game, which could help to explain the evolution of altruism.