Re-conceptualising the Language Game Paradigm in the Framework of Multi-Agent Reinforcement Learning
arXiv:2004.04722
Abstract
In this paper, we formulate the challenge of re-conceptualising the language game experimental paradigm in the framework of multi-agent reinforcement learning (MARL). If successful, future language game experiments will benefit from the rapid and promising methodological advances in the MARL community, while future MARL experiments on learning emergent communication will benefit from the insights and results gained from language game experiments. We strongly believe that this cross-pollination has the potential to lead to major breakthroughs in the modelling of how human-like languages can emerge and evolve in multi-agent systems.
arXiv commentThis paper was accepted for presentation at the 2020 AAAI Spring Symposium `Challenges and Opportunities for Multi-Agent Reinforcement Learning' after a double-blind reviewing process
References in corpus (6)
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- Sharp transition towards shared vocabularies in multi-agent systems
- Cultural route to the emergence of linguistic categories
- Emergent Communication through Negotiation
- Emergence of Communication in an Interactive World with Consistent Speakers
- Vehicle Communication Strategies for Simulated Highway Driving