AAAI 2020 accepted papers on Multi-agent systems and games
73 of the 1,610 papers accepted at AAAI 2020 (4.5%) are on Multi-agent systems and games, compared with 5.1% at AAAI 2019. They fall into 4 topics.
See AAAI 2020 in the interactive map
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 · 29 papers
- Interactive Fiction Games: A Colossal Adventure (158 citations)
- From Few to More: Large-Scale Dynamic Multiagent Curriculum Learning (119 citations)
- Learning to Follow Directions in Street View (63 citations)
- Just Ask: An Interactive Learning Framework for Vision and Language Navigation (60 citations)
- Multi-Objective Multi-Agent Planning for Jointly Discovering and Tracking Mobile Objects (40 citations)
- Idle Time Optimization for Target Assignment and Path Finding in Sortation Centers (36 citations)
- AATEAM: Achieving the Ad Hoc Teamwork by Employing the Attention Mechanism (28 citations)
- ALOHA: Artificial Learning of Human Attributes for Dialogue Agents (26 citations)
- Learning and Reasoning for Robot Sequential Decision Making under Uncertainty (26 citations)
- Learning to Interactively Learn and Assist (21 citations)
- Generating Interactive Worlds with Text (20 citations)
- Generative Attention Networks for Multi-Agent Behavioral Modeling (19 citations)
and 17 more in the interactive map.
Games and equilibria · 25 papers
- Mastering Complex Control in MOBA Games with Deep Reinforcement Learning (342 citations)
- Bi-Level Actor-Critic for Multi-Agent Coordination (86 citations)
- On the Convergence of Model Free Learning in Mean Field Games (66 citations)
- Reinforcement Mechanism Design: With Applications to Dynamic Pricing in Sponsored Search Auctions (61 citations)
- Deep Reinforcement Learning for General Game Playing (50 citations)
- Improving Policies via Search in Cooperative Partially Observable Games (46 citations)
- LTLƒ Synthesis with Fairness and Stability Assumptions (28 citations)
- Algorithmic Improvements for Deep Reinforcement Learning Applied to Interactive Fiction (17 citations)
- Accelerating and Improving AlphaZero Using Population Based Training (16 citations)
- Subsidy Allocations in the Presence of Income Shocks (16 citations)
- Information Elicitation Mechanisms for Statistical Estimation (12 citations)
- Optimal Common Contract with Heterogeneous Agents (12 citations)
and 13 more in the interactive map.
Cooperative multi-agent RL · 17 papers
- Google Research Football: A Novel Reinforcement Learning Environment (316 citations)
- Multi-Agent Game Abstraction via Graph Attention Neural Network (283 citations)
- Multi-Agent Actor-Critic with Hierarchical Graph Attention Network (140 citations)
- Shapley Q-Value: A Local Reward Approach to Solve Global Reward Games (117 citations)
- Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning (87 citations)
- Learning Agent Communication under Limited Bandwidth by Message Pruning (85 citations)
- Partner Selection for the Emergence of Cooperation in Multi-Agent Systems Using Reinforcement Learning (45 citations)
- Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence (30 citations)
- Learning to Communicate Implicitly by Actions (26 citations)
- Continuous Multiagent Control Using Collective Behavior Entropy for Large-Scale Home Energy Management (17 citations)
- SMIX(λ): Enhancing Centralized Value Functions for Cooperative Multi-Agent Reinforcement Learning (17 citations)
- Communication Learning via Backpropagation in Discrete Channels with Unknown Noise (16 citations)
and 5 more in the interactive map.
