AAAI 2023 accepted papers on Multi-agent systems and games
102 of the 2,023 papers accepted at AAAI 2023 (5.0%) are on Multi-agent systems and games, compared with 4.7% at AAAI 2022. They fall into 3 topics.
See AAAI 2023 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Human-AI and goal-conditioned · 55 papers
- LaCAM: Search-Based Algorithm for Quick Multi-Agent Pathfinding (74 citations)
- Intersection Coordination with Priority-Based Search for Autonomous Vehicles (37 citations)
- Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination (20 citations)
- Collective Intelligence in Human-AI Teams: A Bayesian Theory of Mind Approach (19 citations)
- Help Me Heal: A Reinforced Polite and Empathetic Mental Health and Legal Counseling Dialogue System for Crime Victims (16 citations)
- Safe Interval Path Planning with Kinodynamic Constraints (16 citations)
- Foundations of Cooperative AI (15 citations)
- Learning Affects Trust: Design Recommendations and Concepts for Teaching Children—and Nearly Anyone—about Conversational Agents (13 citations)
- Augmenting Flight Training with AI to Efficiently Train Pilots (12 citations)
- Customer Service Combining Human Operators and Virtual Agents: A Call for Multidisciplinary AI Research (12 citations)
- Layout-Aware Dreamer for Embodied Visual Referring Expression Grounding (12 citations)
- Multi-Level Compositional Reasoning for Interactive Instruction Following (8 citations)
and 43 more in the interactive map.
Games and equilibria · 25 papers
- Emergence of Punishment in Social Dilemma with Environmental Feedback (30 citations)
- Finding Fair Allocations under Budget Constraints (14 citations)
- How to Cut a Discrete Cake Fairly (12 citations)
- Causes of Stability in Dynamic Coalition Formation (8 citations)
- Topological Distance Games (6 citations)
- A Pair-Approximation Method for Modelling the Dynamics of Multi-Agent Stochastic Games (5 citations)
- Fairness Concepts for Indivisible Items with Externalities (5 citations)
- Partitioning Friends Fairly (5 citations)
- Collusion-Proof and Sybil-Proof Reward Mechanisms for Query Incentive Networks (4 citations)
- Formal Verification of Bayesian Mechanisms (4 citations)
- Commitment Games with Conditional Information Disclosure (3 citations)
- Multi-Stage Facility Location Problems with Transient Agents (3 citations)
and 13 more in the interactive map.
Cooperative multi-agent RL · 22 papers
- Effective and Stable Role-Based Multi-Agent Collaboration by Structural Information Principles (45 citations)
- Quantum Multi-Agent Meta Reinforcement Learning (40 citations)
- ACE: Cooperative Multi-Agent Q-learning with Bidirectional Action-Dependency (28 citations)
- Consensus Learning for Cooperative Multi-Agent Reinforcement Learning (28 citations)
- Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition (26 citations)
- HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism (24 citations)
- DACOM: Learning Delay-Aware Communication for Multi-Agent Reinforcement Learning (20 citations)
- Robust Multi-Agent Coordination via Evolutionary Generation of Auxiliary Adversarial Attackers (20 citations)
- Subspace-Aware Exploration for Sparse-Reward Multi-Agent Tasks (15 citations)
- Models as Agents: Optimizing Multi-Step Predictions of Interactive Local Models in Model-Based Multi-Agent Reinforcement Learning (13 citations)
- Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning (8 citations)
- Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning (8 citations)
and 10 more in the interactive map.