https://openai.com/blog/learning-to-communicate/

https://arxiv.org/abs/1602.02672v1 Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks

https://arxiv.org/abs/1605.06676v2 Learning to Communicate with Deep Multi-Agent Reinforcement Learning

https://arxiv.org/abs/1608.06409v1 Learning to Communicate: Channel Auto-encoders, Domain Specific Regularizers, and Attention

https://arxiv.org/abs/1611.01796v1 Modular Multitask Reinforcement Learning with Policy Sketches

https://arxiv.org/abs/1606.02447v1 Learning Language Games through Interaction

https://arxiv.org/abs/1703.04908 Emergence of Grounded Compositional Language in Multi-Agent Populations

https://arxiv.org/abs/1610.03585 A Paradigm for Situated and Goal-Driven Language Learning

https://arxiv.org/pdf/1703.10069v1.pdf Multiagent Bidirectionally-Coordinated Nets for Learning to Play StarCraft Combat Games

https://arxiv.org/abs/1704.06960v1 Translating Neuralese https://github.com/jacobandreas/neuralese

https://arxiv.org/abs/1705.11192v1 Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols

https://arxiv.org/pdf/1705.10369.pdf Emergent Language in a Multi-Modal, Multi-Step Referential Game

Inspired by previous work on emergent language in referential games, we propose a novel multi-modal, multi-step referential game, where the sender and receiver have access to distinct modalities of an object, and their information exchange is bidirectional and of arbitrary duration. The multi-modal multi-step setting allows agents to develop an internal language significantly closer to natural language, in that they share a single set of messages, and that the length of the conversation may vary according to the difficulty of the task. We examine these properties empirically using a dataset consisting of images and textual descriptions of mammals, where the agents are tasked with identifying the correct object. Our experiments indicate that a robust and efficient communication protocol emerges, where gradual information exchange informs better predictions and higher communication bandwidth improves generalization. https://github.com/nyu-dl/MultimodalGame