ICML 2022 accepted papers on Multi-agent systems and games
30 of the 1,233 papers accepted at ICML 2022 (2.4%) are on Multi-agent systems and games, compared with 3.5% at ICML 2021. They fall into 3 topics.
See ICML 2022 in the interactive map
Submitting to ICML? 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
Cooperative multi-agent RL · 15 papers
- Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning (14 citations)
- MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer (9 citations)
- PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration (7 citations)
- Decentralized Online Convex Optimization in Networked Systems (5 citations)
- On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning (4 citations)
- Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL (4 citations)
- Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis (4 citations)
- Divergence-Regularized Multi-Agent Actor-Critic (2 citations)
- Greedy based Value Representation for Optimal Coordination in Multi-agent Reinforcement Learning (2 citations)
- Self-Organized Polynomial-Time Coordination Graphs (2 citations)
- A Regret Minimization Approach to Multi-Agent Control (1 citation)
- Deconfounded Value Decomposition for Multi-Agent Reinforcement Learning
and 3 more in the interactive map.
Human-AI and goal-conditioned · 9 papers
- DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations (11 citations)
- Tell me why! Explanations support learning relational and causal structure (9 citations)
- A data-driven approach for learning to control computers (7 citations)
- Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning (4 citations)
- A Framework for Learning to Request Rich and Contextually Useful Information from Humans (3 citations)
- Asking for Knowledge (AFK): Training RL Agents to Query External Knowledge Using Language (2 citations)
- Fast Population-Based Reinforcement Learning on a Single Machine (1 citation)
- How to Stay Curious while avoiding Noisy TVs using Aleatoric Uncertainty Estimation (1 citation)
- Symmetric Machine Theory of Mind
Games and equilibria · 6 papers
- The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces (5 citations)
- COLA: Consistent Learning with Opponent-Learning Awareness (2 citations)
- Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation (1 citation)
- Interactive Inverse Reinforcement Learning for Cooperative Games (1 citation)
- Generalized Beliefs for Cooperative AI
- On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated Games
