ICLR 2019 accepted papers on Multi-agent systems and games
15 of the 502 papers accepted at ICLR 2019 (3.0%) are on Multi-agent systems and games, compared with 4.7% at ICLR 2018. They fall into 3 topics.
See ICLR 2019 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 · 10 papers
- Self-Monitoring Navigation Agent via Auxiliary Progress Estimation (185 citations)
- Deep reinforcement learning with relational inductive biases (130 citations)
- Emergent Coordination Through Competition (81 citations)
- BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning (66 citations)
- Learning to Understand Goal Specifications by Modelling Reward (62 citations)
- Generating Multi-Agent Trajectories using Programmatic Weak Supervision (52 citations)
- StrokeNet: A Neural Painting Environment (52 citations)
- Relational Forward Models for Multi-Agent Learning (51 citations)
- Stochastic Prediction of Multi-Agent Interactions from Partial Observations (31 citations)
- Multi-Agent Dual Learning
Cooperative multi-agent RL · 3 papers
Games and equilibria · 2 papers
- Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning (48 citations)
- Stable Opponent Shaping in Differentiable Games (10 citations)
