ICML 2023 accepted papers on Multi-agent systems and games
44 of the 1,865 papers accepted at ICML 2023 (2.4%) are on Multi-agent systems and games, compared with 2.4% at ICML 2022. They fall into 3 topics.
See ICML 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 · 18 papers
- Guiding Pretraining in Reinforcement Learning with Large Language Models (37 citations)
- Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark (26 citations)
- Language Instructed Reinforcement Learning for Human-AI Coordination (10 citations)
- Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling (8 citations)
- Adaptive Coordination in Social Embodied Rearrangement (5 citations)
- Distilling Internet-Scale Vision-Language Models into Embodied Agents (3 citations)
- Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learning (3 citations)
- MyoDex: A Generalizable Prior for Dexterous Manipulation (3 citations)
- Controlling Type Confounding in Ad Hoc Teamwork with Instance-wise Teammate Feedback Rectification (2 citations)
- Curious Replay for Model-based Adaptation (2 citations)
- Entity Divider with Language Grounding in Multi-Agent Reinforcement Learning (2 citations)
- K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs (1 citation)
and 6 more in the interactive map.
Cooperative multi-agent RL · 13 papers
- Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation (4 citations)
- Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observability (2 citations)
- Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation (2 citations)
- Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning (2 citations)
- Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning (1 citation)
- An Adaptive Entropy-Regularization Framework for Multi-Agent Reinforcement Learning
- MANSA: Learning Fast and Slow in Multi-Agent Systems
- N$\text{A}^\text{2}$Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning
- Complementary Attention for Multi-Agent Reinforcement Learning
- Lazy Agents: A New Perspective on Solving Sparse Reward Problem in Multi-agent Reinforcement Learning
- Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing
- Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning
and 1 more in the interactive map.
Games and equilibria · 13 papers
- Explaining Reinforcement Learning with Shapley Values (6 citations)
- A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems (3 citations)
- Cooperative Open-ended Learning Framework for Zero-Shot Coordination (2 citations)
- Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games (2 citations)
- Social learning spontaneously emerges by searching optimal heuristics with deep reinforcement learning (1 citation)
- Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games
- Multi-Agent Best Arm Identification with Private Communications
- Multi-agent Online Scheduling: MMS Allocations for Indivisible Items
- Oracles & Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learning
- Learning to Optimize Differentiable Games
- Multi-Agent Learning from Learners
- Network Effects in Performative Prediction Games
and 1 more in the interactive map.