ICLR 2020 accepted papers on Multi-agent systems and games
29 of the 687 papers accepted at ICLR 2020 (4.2%) are on Multi-agent systems and games, compared with 3.0% at ICLR 2019. They fall into 3 topics.
See ICLR 2020 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 · 19 papers
- Emergent Tool Use From Multi-Agent Autocurricula (372 citations)
- Dream to Control: Learning Behaviors by Latent Imagination (131 citations)
- Environmental drivers of systematicity and generalization in a situated agent (84 citations)
- Graph Constrained Reinforcement Learning for Natural Language Action Spaces (61 citations)
- Making Efficient Use of Demonstrations to Solve Hard Exploration Problems (50 citations)
- Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning (43 citations)
- Compositional languages emerge in a neural iterated learning model (33 citations)
- Graph Convolutional Reinforcement Learning (32 citations)
- Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution (31 citations)
- On the interaction between supervision and self-play in emergent communication (30 citations)
- Combining Q-Learning and Search with Amortized Value Estimates (27 citations)
- RTFM: Generalising to New Environment Dynamics via Reading (26 citations)
and 7 more in the interactive map.
Cooperative multi-agent RL · 8 papers
- Multi-agent Reinforcement Learning for Networked System Control (69 citations)
- CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning (40 citations)
- Learning Nearly Decomposable Value Functions Via Communication Minimization (24 citations)
- Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning (14 citations)
- Action Semantics Network: Considering the Effects of Actions in Multiagent Systems (12 citations)
- Influence-Based Multi-Agent Exploration (4 citations)
- Learning Expensive Coordination: An Event-Based Deep RL Approach (4 citations)
- Multi-Agent Interactions Modeling with Correlated Policies (3 citations)
