ICLR 2022 accepted papers on Multi-agent systems and games
33 of the 1,095 papers accepted at ICLR 2022 (3.0%) are on Multi-agent systems and games, compared with 2.9% at ICLR 2021. They fall into 3 topics.
See ICLR 2022 in the interactive map
Submitting to ICLR? 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 · 21 papers
- THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling (57 citations)
- Latent Variable Sequential Set Transformers for Joint Multi-Agent Motion Prediction (38 citations)
- ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind (19 citations)
- Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization (15 citations)
- Sound Adversarial Audio-Visual Navigation (7 citations)
- Learning to Map for Active Semantic Goal Navigation (4 citations)
- On the role of population heterogeneity in emergent communication (4 citations)
- Procedural generalization by planning with self-supervised world models (4 citations)
- You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction (4 citations)
- Cross-Domain Imitation Learning via Optimal Transport (3 citations)
- A First-Occupancy Representation for Reinforcement Learning (2 citations)
- In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications (2 citations)
and 9 more in the interactive map.
Cooperative multi-agent RL · 10 papers
- Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning (82 citations)
- Context-Aware Sparse Deep Coordination Graphs (6 citations)
- Dealing with Non-Stationarity in MARL via Trust-Region Decomposition (4 citations)
- Multi-Agent MDP Homomorphic Networks (4 citations)
- LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent Learning (3 citations)
- Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming (2 citations)
- Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games
- Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach
- Finite-Time Convergence and Sample Complexity of Multi-Agent Actor-Critic Reinforcement Learning with Average Reward
- Reinforcement Learning under a Multi-agent Predictive State Representation Model: Method and Theory
