Related papers: Emergent Coordination Through Competition
Reinforcement learning has the potential to automate the acquisition of behavior in complex settings, but in order for it to be successfully deployed, a number of practical challenges must be addressed. First, in real world settings, when…
We consider the problem of robust multi-agent reinforcement learning (MARL) for cooperative communication and coordination tasks. MARL agents, mainly those trained in a centralized way, can be brittle because they can adopt policies that…
Human players in professional team sports achieve high level coordination by dynamically choosing complementary skills and executing primitive actions to perform these skills. As a step toward creating intelligent agents with this…
Social dilemmas, where mutual cooperation can lead to high payoffs but participants face incentives to cheat, are ubiquitous in multi-agent interaction. We wish to construct agents that cooperate with pure cooperators, avoid exploitation by…
Situations of conflict giving rise to social dilemmas are widespread in society and game theory is one major way in which they can be investigated. Starting from the observation that individuals in society interact through networks of…
Many real-world scenarios involve teams of agents that have to coordinate their actions to reach a shared goal. We focus on the setting in which a team of agents faces an opponent in a zero-sum, imperfect-information game. Team members can…
In this paper, we elaborate on the design and discuss the results of a multi-agent simulation that we have developed using the PSI cognitive architecture. We demonstrate that imbuing agents with intrinsic needs for group affiliation,…
We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment,…
The universe involves many independent co-learning agents as an ever-evolving part of our observed environment. Yet, in practice, Multi-Agent Reinforcement Learning (MARL) applications are typically constrained to small, homogeneous…
In many situations, communication between agents is a critical component of cooperative multi-agent systems, however, it can be difficult to learn or evolve. In this paper, we investigate a simple way in which the emergence of communication…
This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) that combines cooperative task decomposition with the learning of reward machines (RMs) encoding the structure of the sub-tasks. The proposed method helps…
This paper seeks to combine differential game theory with the actor-critic-identifier architecture to determine forward-in-time, approximate optimal controllers for formation tracking in multi-agent systems, where the agents have uncertain…
Constrained multi-agent reinforcement learning offers the framework to design scalable and almost surely feasible solutions for teams of agents operating in dynamic environments to carry out conflicting tasks. We address the challenges of…
Collaborating with humans requires rapidly adapting to their individual strengths, weaknesses, and preferences. Unfortunately, most standard multi-agent reinforcement learning techniques, such as self-play (SP) or population play (PP),…
The theory of learning in games has extensively studied situations where agents respond dynamically to each other by optimizing a fixed utility function. However, in real situations, the strategic environment varies as a result of past…
This work studies the problem of ad hoc teamwork in teams composed of agents with differing computational capabilities. We consider cooperative multi-player games in which each agent's policy is constrained by a private capability…
Dynamics of a social population is analyzed taking into account some physical constraints on individual behavior and decision making abilities. The model, based on Evolutionary Game Theory, predicts that a population has to pass through a…
We focus on how individual behavior that complies with social norms interferes with performance-based incentive mechanisms in organizations with multiple distributed decision-making agents. We model social norms to emerge from interactions…
Multi-agent Reinforcement Learning (MARL) is a powerful tool for training autonomous agents acting independently in a common environment. However, it can lead to sub-optimal behavior when individual incentives and group incentives diverge.…
Collective behavior, and swarm formation in particular, has been studied from several perspectives within a large variety of fields, ranging from biology to physics. In this work, we apply Projective Simulation to model each individual as…