AI agents invented their own language in an OpenAI experiment. "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. Goals can vary from looking at or moving to a specific location, to encouraging a separate agent to move to a location. Each agent can broadcast messages to the group. Every agent's reward is the sum of the rewards paid out to all agents, encouraging collaboration."

"Our agents evolve languages to fit the complexity of their situation, with solitary agents not needing to communicate, two agents inventing one-word phrases to coordinate with each other in simple tasks, and three agents composing multiple words in sentences to accomplish more challenging tasks."

(A "word" here is actually a one-hot vector.)
Shared publiclyView activity