Social Environment Design
Not on the map. Why?
Abstract (arXiv)
Artificial Intelligence (AI) holds promise as a technology that can be used to improve government and economic policy-making. This paper proposes a new research agenda towards this end by introducing Social Environment Design, a general framework for the use of AI for automated policy-making that connects with the Reinforcement Learning, EconCS, and Computational Social Choice communities. The framework seeks to capture general economic environments, includes voting on policy objectives, and gives a direction for the systematic analysis of government and economic policy through AI simulation. We highlight key open problems for future research in AI-based policy-making. By solving these challenges, we hope to achieve various social welfare objectives, thereby promoting more ethical and responsible decision making.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 45 of its 91 references that are in the map. First posted on arXiv 21 Feb 2024.
Builds on
45 of 91 references.
References · 45
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
- 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
- 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
- 2017Counterfactual Multi-Agent Policy Gradientscited by 733
- 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
- 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 372
- 2020Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 197
- 2021Trust Region Policy Optimisation in Multi-Agent Reinforcement Learningcited by 180
- 2020FACMAC: Factored Multi-Agent Centralised Policy Gradientscited by 178
- 2022Multi-Agent Reinforcement Learning is a Sequence Modeling Problemcited by 153
- 2018Graph Convolutional Reinforcement Learningcited by 148
33 more
- 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 135
- 2020RODE: Learning Roles to Decompose Multi-Agent Taskscited by 125
- 2018Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Taskscited by 114
- 2020Shared Experience Actor-Critic for Multi-Agent Reinforcement Learningcited by 114
- 2020Off-Policy Multi-Agent Decomposed Policy Gradientscited by 97
- 2019Deep Coordination Graphscited by 96
- 2021Celebrating Diversity in Shared Multi-Agent Reinforcement Learningcited by 96
- 2019Learning Nearly Decomposable Value Functions Via Communication Minimizationcited by 85
- 2019Influence-Based Multi-Agent Explorationcited by 75
- 2017A multi-agent reinforcement learning model of common-pool resource appropriationcited by 68
- 2017Optimal Auctions through Deep Learning: Advances in Differentiable Economicscited by 38
- 2022Melting Pot 2.0cited by 37
- 2018Automated Mechanism Design via Neural Networkscited by 31
- 2021Context-Aware Sparse Deep Coordination Graphscited by 27
- 2022Optimal-er Auctions through Attentioncited by 26
- 2019Modelling Bounded Rationality in Multi-Agent Interactions by Generalized Recursive Reasoningcited by 24
- 2023A Scalable Neural Network for DSIC Affine Maximizer Auction Designcited by 23
- 2018M3RL: Mind-aware Multi-agent Management Reinforcement Learningcited by 22
- 2021Adaptive Incentive Design with Multi-Agent Meta-Gradient Reinforcement Learningcited by 18
- 2019Neighborhood Cognition Consistent Multi-Agent Reinforcement Learningcited by 17
- 2022Low-Rank Modular Reinforcement Learning via Muscle Synergycited by 16
- 2020Incorporating Pragmatic Reasoning Communication into Emergent Languagecited by 15
- 2021Learning Revenue-Maximizing Auctions With Differentiable Matchingcited by 14
- 2021Self-Organized Polynomial-Time Coordination Graphscited by 14
- 2023Symmetry-Aware Robot Design with Structured Subgroupscited by 13
- 2022Oracles & Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learningcited by 12
- 2021Coordinating Followers to Reach Better Equilibria: End-to-End Gradient Descent for Stackelberg Gamescited by 10
- 2022Non-Linear Coordination Graphscited by 10
- 2023Deep Contract Design via Discontinuous Networkscited by 10
- 2024Multi-Sender Persuasion: A Computational Perspectivecited by 9
- 2017Methods for finding leader--follower equilibria with multiple followerscited by 3
- 2023Enabling First-Order Gradient-Based Learning for Equilibrium Computation in Marketscited by 3
- 2022HCMD-zero: Learning Value Aligned Mechanisms from Datacited by 2
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.