Learning to Communicate
▻https://blog.openai.com/learning-to-communicate
To train the agents, we represent the experiment as a cooperative — rather than competitive — multi-agent reinforcement learning problem. The agents exist in a two-dimensional world with simple landmarks, and each agent has a goal.
#évolution #langage #IA #machine-learning
▻https://www.wired.com/2017/03/openai-builds-bots-learn-speak-language