Games Under Network Uncertainty
We examine settings in which agents choose behaviors and care about their neighbors' behaviors, but have incomplete information about the network in which they are embedded. We develop a model in which agents use local knowledge of their direct (and in some cases indirect) connections to make inferences about the complementarity strength of their actions with other agents in the society. Consequently, an agent's position in the network and identity plays a crucial role in determining their strategic behavior in ways that we can quantify. Our main results characterize equilibrium behaviors under various beliefs. In particular, we analyze the role of heterogeneous network information among agents in detail. For instance, we show how having people update about the network can lead those with lower degree to systematically underestimate the complementarities in the society, while those with higher degree overestimate the complementarities. We also study the inferences that agents make and the resulting behaviors in several prominent families of network architectures.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Risk-Sensitive Bayesian Games for Multi-Agent Reinforcement Learning under Policy Uncertainty
In stochastic games with incomplete information, the uncertainty is evoked by the lack of knowledge about a player's own and the other players' types, i.e. the utility function and the policy space, and also the inherent…
Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning (RL)A Review of Uncertainty for Deep Reinforcement Learning
Uncertainty is ubiquitous in games, both in the agents playing games and often in the games themselves. Working with uncertainty is therefore an important component of successful deep reinforcement learning agents. While…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)The impact of uncertainty on regularized learning in games
In this paper, we investigate how randomness and uncertainty influence learning in games. Specifically, we examine a perturbed variant of the dynamics of "follow-the-regularized-leader" (FTRL), where the players' payoff …
The Evolution of Uncertainty of Learning in Games
Learning in games has become an object of intense interest for ML due to its connections to numerous AI architectures. We study standard online learning in games but from a non-standard perspective. Instead of studying t…
Teamwork under extreme uncertainty: AI for Pokemon ranks 33rd in the world
The highest grossing media franchise of all times, with over \$90 billion in total revenue, is Pokemon. The video games belong to the class of Japanese Role Playing Games (J-RPG). Developing a powerful AI agent for these…
AI Agent