ICLR 2018 accepted papers on Multi-agent systems and games
16 of the 337 papers accepted at ICLR 2018 (4.7%) are on Multi-agent systems and games, compared with 5.1% at ICLR 2017. They fall into 2 topics.
See ICLR 2018 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 · 14 papers
- Noisy Networks For Exploration (571 citations)
- Distributed Prioritized Experience Replay (487 citations)
- Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play (131 citations)
- Neural Map: Structured Memory for Deep Reinforcement Learning (99 citations)
- Active Neural Localization (54 citations)
- Compositional Obverter Communication Learning from Raw Visual Input (52 citations)
- Semi-parametric topological memory for navigation (52 citations)
- Emergent Translation in Multi-Agent Communication (50 citations)
- Emergent Communication through Negotiation (43 citations)
- Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input (31 citations)
- Emergent Communication in a Multi-Modal, Multi-Step Referential Game (27 citations)
- Learning Awareness Models (10 citations)
and 2 more in the interactive map.
