NeurIPS 2019 accepted papers on Multi-agent systems and games
30 of the 1,429 papers accepted at NeurIPS 2019 (2.1%) are on Multi-agent systems and games, compared with 1.5% at NeurIPS 2018. They fall into 3 topics.
See NeurIPS 2019 in the interactive map
Submitting to NeurIPS? 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 · 14 papers
- Multiple Futures Prediction (115 citations)
- On the Utility of Learning about Humans for Human-AI Coordination (88 citations)
- Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity (63 citations)
- Discovery of Useful Questions as Auxiliary Tasks (31 citations)
- Ease-of-Teaching and Language Structure from Emergent Communication (27 citations)
- Towards Interpretable Reinforcement Learning Using Attention Augmented Agents (26 citations)
- Modeling Conceptual Understanding in Image Reference Games (24 citations)
- Learning to Predict Without Looking Ahead: World Models Without Forward Prediction (20 citations)
- Symmetry-Based Disentangled Representation Learning requires Interaction with Environments (15 citations)
- Interval timing in deep reinforcement learning agents (10 citations)
- Compositional Plan Vectors (7 citations)
- Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction (4 citations)
and 2 more in the interactive map.
Cooperative multi-agent RL · 9 papers
- LIIR: Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning (75 citations)
- MAVEN: Multi-Agent Variational Exploration (67 citations)
- Multi-Agent Common Knowledge Reinforcement Learning (50 citations)
- Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning (33 citations)
- Biases for Emergent Communication in Multi-agent Reinforcement Learning (28 citations)
- Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control (24 citations)
- Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning (22 citations)
- A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning (12 citations)
- Learning Fairness in Multi-Agent Systems (11 citations)
Games and equilibria · 7 papers
- Finding Friend and Foe in Multi-Agent Games (27 citations)
- Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach (23 citations)
- No-Press Diplomacy: Modeling Multi-Agent Gameplay (15 citations)
- Non-Cooperative Inverse Reinforcement Learning (15 citations)
- Distinguishing Distributions When Samples Are Strategically Transformed (7 citations)
- Learning Mean-Field Games (7 citations)
- Robust Multi-agent Counterfactual Prediction (7 citations)
