Prosocial Learning Agents Solve Generalized Stag Hunts Better Than Selfish Ones

Abstract

Deep reinforcement learning has become an important paradigm for constructing agents that can enter complex multi-agent situations and improve their policies through experience. One commonly used technique is reactive training - applying standard RL methods while treating other agents as a part of the learner's environment. It is known that in general-sum games reactive training can lead groups of agents to converge to inefficient outcomes. We focus on one such class of environments: Stag Hunt games. Here agents either choose a risky cooperative policy (which leads to high payoffs if both choose it but low payoffs to an agent who attempts it alone) or a safe one (which leads to a safe payoff no matter what). We ask how we can change the learning rule of a single agent to improve its outcomes in Stag Hunts that include other reactive learners. We extend existing work on reward-shaping in multi-agent reinforcement learning and show that that making a single agent prosocial, that is, maki

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypeysakhovich2017prosocial

Related papers

• Exploring The Impact Of Tunable Agents In Sequential Social Dilemmas (2021)0.00
• Training Generalizable Collaborative Agents Via Strategic Risk Aversion (2026)0.00
• Social Learning Spontaneously Emerges By Searching Optimal Heuristics With Deep Reinforcement Learning (2022)0.00
• Multi-agent Cooperation Through Learning-aware Policy Gradients (2024)0.00
• Reciprocal Reward Influence Encourages Cooperation From Self-interested Agents (2024)1.91
• Evolutionary Multi-agent Reinforcement Learning In Group Social Dilemmas (2024)0.00
• Modeling Human Reputation-seeking Behavior In A Spatio-temporally Complex Public Good Provision Game (2025)0.00
• Discovering Diverse Multi-agent Strategic Behavior Via Reward Randomization (2021)0.00