NeurIPS 2022 accepted papers on Multi-agent systems and games
92 of the 2,901 papers accepted at NeurIPS 2022 (3.2%) are on Multi-agent systems and games, compared with 3.2% at NeurIPS 2021. They fall into 3 topics.
See NeurIPS 2022 in the interactive map
Submitting to NeurIPS? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Human-AI and goal-conditioned · 37 papers
- Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps (96 citations)
- MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge (59 citations)
- WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents (51 citations)
- Multi-Game Decision Transformers (27 citations)
- Interaction Modeling with Multiplex Attention (11 citations)
- Towards Versatile Embodied Navigation (10 citations)
- Model-Based Opponent Modeling (9 citations)
- Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world (9 citations)
- DMAP: a Distributed Morphological Attention Policy for learning to locomote with a changing body (8 citations)
- Inherently Explainable Reinforcement Learning in Natural Language (8 citations)
- Parametrically Retargetable Decision-Makers Tend To Seek Power (8 citations)
- Ask4Help: Learning to Leverage an Expert for Embodied Tasks (5 citations)
and 25 more in the interactive map.
Cooperative multi-agent RL · 37 papers
- The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games (597 citations)
- Multi-Agent Reinforcement Learning is a Sequence Modeling Problem (79 citations)
- LDSA: Learning Dynamic Subtask Assignment in Cooperative Multi-Agent Reinforcement Learning (21 citations)
- ALMA: Hierarchical Learning for Composite Multi-Agent Tasks (9 citations)
- SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning (9 citations)
- Towards a Standardised Performance Evaluation Protocol for Cooperative MARL (9 citations)
- Rethinking Individual Global Max in Cooperative Multi-Agent Reinforcement Learning (8 citations)
- Efficient Multi-agent Communication via Self-supervised Information Aggregation (7 citations)
- Multi-agent Dynamic Algorithm Configuration (7 citations)
- ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward (6 citations)
- I2Q: A Fully Decentralized Q-Learning Algorithm (6 citations)
- Self-Organized Group for Cooperative Multi-agent Reinforcement Learning (6 citations)
and 25 more in the interactive map.
Games and equilibria · 18 papers
- PerfectDou: Dominating DouDizhu with Perfect Information Distillation (14 citations)
- Sample-Efficient Reinforcement Learning of Partially Observable Markov Games (7 citations)
- Inverse Game Theory for Stackelberg Games: the Blessing of Bounded Rationality (6 citations)
- How and Why to Manipulate Your Own Agent: On the Incentives of Users of Learning Agents (5 citations)
- Near-Optimal Multi-Agent Learning for Safe Coverage Control (4 citations)
- A Mean-Field Game Approach to Cloud Resource Management with Function Approximation (3 citations)
- A Unified Diversity Measure for Multiagent Reinforcement Learning (3 citations)
- Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergence (3 citations)
- Peer Prediction for Learning Agents (2 citations)
- Learning NP-Hard Multi-Agent Assignment Planning using GNN: Inference on a Random Graph and Provable Auction-Fitted Q-learning (1 citation)
- Multi-agent Performative Prediction with Greedy Deployment and Consensus Seeking Agents (1 citation)
- Envy-free Policy Teaching to Multiple Agents
and 6 more in the interactive map.
