Stochastic Market Games

Abstract

Some of the most relevant future applications of multi-agent systems like autonomous driving or factories as a service display mixed-motive scenarios, where agents might have conflicting goals. In these settings agents are likely to learn undesirable outcomes in terms of cooperation under independent learning, such as overly greedy behavior. Motivated from real world societies, in this work we propose to utilize market forces to provide incentives for agents to become cooperative. As demonstrated in an iterated version of the Prisoner's Dilemma, the proposed market formulation can change the dynamics of the game to consistently learn cooperative policies. Further we evaluate our approach in spatially and temporally extended settings for varying numbers of agents. We empirically find that the presence of markets can improve both the overall result and agent individual returns via their trading activities.

arXiv commentIJCAI-21

References in corpus (4)

• Multi-agent Reinforcement Learning in Sequential Social Dilemmas
• Maintaining cooperation in complex social dilemmas using deep reinforcement learning
• A multi-agent reinforcement learning model of common-pool resource appropriation
• Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions