# Prosocial learning agents solve generalized Stag Hunts better than selfish ones

arXiv: https://arxiv.org/abs/1709.02865 · HTML: https://mlsanity.com/paper/1709.02865/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2017.

## Built on by (most cited first, 30 of 47)

- [Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot](https://mlsanity.com/paper/2107.06857/) (2021)
- [Deep Multiagent Reinforcement Learning: Challenges and Directions](https://mlsanity.com/paper/2106.15691/) (2021)
- [Melting Pot 2.0](https://mlsanity.com/paper/2211.13746/) (2022)
- [Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization](https://mlsanity.com/paper/2103.04564/) (2021)
- [A Review of Cooperation in Multi-agent Learning](https://mlsanity.com/paper/2312.05162/) (2023)
- [A social path to human-like artificial intelligence](https://mlsanity.com/paper/2405.15815/) (2024)
- [Multi-Agent Path Finding with Prioritized Communication Learning](https://mlsanity.com/paper/2202.03634/) (2022)
- [Survey on Fair Reinforcement Learning: Theory and Practice](https://mlsanity.com/paper/2205.10032/) (2022)
- [A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems](https://mlsanity.com/paper/2205.15434/) (2022)
- [Cooperation and Reputation Dynamics with Reinforcement Learning](https://mlsanity.com/paper/2102.07523/) (2021)
- [Emergent Prosociality in Multi-Agent Games Through Gifting](https://mlsanity.com/paper/2105.06593/) (2021)
- [Modeling Moral Choices in Social Dilemmas with Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2301.08491/) (2023)
- [Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi](https://mlsanity.com/paper/2308.10284/) (2023)
- [Principal-Agent Reinforcement Learning: Orchestrating AI Agents with Contracts](https://mlsanity.com/paper/2407.18074/) (2024)
- [Joint Attention for Multi-Agent Coordination and Social Learning](https://mlsanity.com/paper/2104.07750/) (2021)
- [Cooperative Multi-Agent Fairness and Equivariant Policies](https://mlsanity.com/paper/2106.05727/) (2021)
- [On-the-fly Strategy Adaptation for ad-hoc Agent Coordination](https://mlsanity.com/paper/2203.08015/) (2022)
- [The Importance of Credo in Multiagent Learning](https://mlsanity.com/paper/2204.07471/) (2022)
- [Aligning Individual and Collective Objectives in Multi-Agent Cooperation](https://mlsanity.com/paper/2402.12416/) (2024)
- [Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning](https://mlsanity.com/paper/2406.08002/) (2024)
- [A multi-agent reinforcement learning model of reputation and cooperation in human groups](https://mlsanity.com/paper/2103.04982/) (2021)
- [Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games](https://mlsanity.com/paper/2410.07863/) (2024)
- [VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments](https://mlsanity.com/paper/2506.02387/) (2025)
- [Learning to Share in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2112.08702/) (2021)
- [Mediated Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2306.08419/) (2023)
- [Reward-Sharing Relational Networks in Multi-Agent Reinforcement Learning as a Framework for Emergent Behavior](https://mlsanity.com/paper/2207.05886/) (2022)
- [Improved Cooperation by Exploiting a Common Signal](https://mlsanity.com/paper/2102.02304/) (2021)
- [Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments](https://mlsanity.com/paper/2102.12307/) (2021)
- [A Minimax Approach to Ad Hoc Teamwork](https://mlsanity.com/paper/2502.02377/) (2025)
- [Learning Roles with Emergent Social Value Orientations](https://mlsanity.com/paper/2301.13812/) (2023)

## Abstract (arXiv)

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, making them care about the rewards of their partners can increase the probability that groups converge to good outcomes. Thus, even if we control a single agent in a group making that agent prosocial can increase our agent's long-run payoff. We show experimentally that this result carries over to a variety of more complex environments with Stag Hunt-like dynamics including ones where agents must learn from raw input pixels.