Multi-agent reinforcement learning

<p>Multi-agent reinforcement learning (MARL) is a sub-field of <a href="/facts/Reinforcement_learning/NrgPPS0Q">reinforcement learning</a>. It focuses on studying the behavior of multiple learning agents that coexist in a shared environment. Each agent is motivated by its own rewards, and does actions to advance its own interests; in some environments these interests are opposed to the interests of other agents, resulting in complex <a href="/facts/Group_dynamics/Jo0C0Dfa">group dynamics</a>.
</p><p>Multi-agent reinforcement learning is closely related to <a href="/facts/Game_theory/zkEIj1ya">game theory</a> and especially <a href="/facts/Repeated_game/xPgL0ta8">repeated games</a>, as well as <a href="/facts/Multi-agent_system/A85vt3UA">multi-agent systems</a>. Its study combines the pursuit of finding ideal algorithms that maximize rewards with a more sociological set of concepts. While research in single-agent reinforcement learning is concerned with finding the algorithm that gets the biggest number of points for one agent, research in multi-agent reinforcement learning evaluates and quantifies social metrics, such as cooperation, reciprocity, equity, social influence, language and discrimination.
</p>

Multi-agent reinforcement learning open-in-new

Multi-agent reinforcement learning