NeurIPS 2023 accepted papers on Multi-agent systems and games
86 of the 3,584 papers accepted at NeurIPS 2023 (2.4%) are on Multi-agent systems and games, compared with 3.2% at NeurIPS 2022. They fall into 4 topics.
See NeurIPS 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 · 39 papers
- How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception (20 citations)
- ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling (19 citations)
- Asynchrony-Robust Collaborative Perception via Bird's Eye View Flow (18 citations)
- Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents (17 citations)
- A Definition of Continual Reinforcement Learning (14 citations)
- Passive learning of active causal strategies in agents and language models (10 citations)
- The Waymo Open Sim Agents Challenge (9 citations)
- Thought Cloning: Learning to Think while Acting by Imitating Human Thinking (9 citations)
- From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces (8 citations)
- An Efficient End-to-End Training Approach for Zero-Shot Human-AI Coordination (5 citations)
- Arbitrarily Scalable Environment Generators via Neural Cellular Automata (5 citations)
- Semantic HELM: A Human-Readable Memory for Reinforcement Learning (5 citations)
and 27 more in the interactive map.
Cooperative multi-agent RL · 21 papers
- SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning (28 citations)
- Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement Learning (15 citations)
- Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization (10 citations)
- Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning (8 citations)
- Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms (7 citations)
- RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization (4 citations)
- Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning (4 citations)
- Decompose a Task into Generalizable Subtasks in Multi-Agent Reinforcement Learning (3 citations)
- Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning (2 citations)
- Gigastep - One Billion Steps per Second Multi-agent Reinforcement Learning (2 citations)
- IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL (2 citations)
- Learning Multi-agent Behaviors from Distributed and Streaming Demonstrations (2 citations)
and 9 more in the interactive map.
Games and equilibria · 20 papers
- Honesty Is the Best Policy: Defining and Mitigating AI Deception (3 citations)
- Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents (2 citations)
- Deep Contract Design via Discontinuous Networks (2 citations)
- Multi-Player Zero-Sum Markov Games with Networked Separable Interactions (2 citations)
- Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games (2 citations)
- A Reduction-based Framework for Sequential Decision Making with Delayed Feedback (1 citation)
- Exponential Lower Bounds for Fictitious Play in Potential Games (1 citation)
- Higher-Order Uncoupled Dynamics Do Not Lead to Nash Equilibrium - Except When They Do (1 citation)
- Multi-Agent Meta-Reinforcement Learning: Sharper Convergence Rates with Task Similarity (1 citation)
- On Imitation in Mean-field Games (1 citation)
- Policy Space Diversity for Non-Transitive Games (1 citation)
- Similarity-based cooperative equilibrium (1 citation)
and 8 more in the interactive map.
LLM agents · 6 papers
- Reflexion: language agents with verbal reinforcement learning (559 citations)
- CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society (148 citations)
- Mind2Web: Towards a Generalist Agent for the Web (69 citations)
- AdaPlanner: Adaptive Planning from Feedback with Language Models (12 citations)
- Large Language Models Are Semi-Parametric Reinforcement Learning Agents (10 citations)
- De novo Drug Design using Reinforcement Learning with Multiple GPT Agents (6 citations)