OpenAI published a post about its findings when using Universe, a software for measuring and training AI agents to conduct reinforcement learning experiments.Universe was used to train an AI system to play the videogame CoastRunners, a plane racing game. Instead of racing toward the finish line, the AI flew circles around an island collecting extra before proceeding. The AI agent scored an average of 20% more points than the human players, however did not carry out the main goal of the videogame itself (competing in the races).

OpenAI published a post about its findings when using Universe, a software for measuring and training AI agents to conduct reinforcement learning experiments, showing that the AI agent did not act in the way intended to complete a videogame.

Unclear/unknown

Universe, a software used to measure and train AI systems to conduct reinforced learning experiments

OpenAI

Professional, scientific and technical activities

Perception, Cognition, Action

Universe software

reinforcement learning training, machine learning

OpenAI, Universe, CoastRunners

OpenAI

2016-12-02T08:00:00.000Z

2016-12-02T08:00:00.000Z

Unclear/unknown

Unclear

No

Universe software training