OpenAI has developed a new class of reinforcement learning algorithms called Proximal Policy Optimization (PPO). These algorithms are simpler to implement and tune than state-of-the-art approaches, yet perform comparably or better. PPO has become the default algorithm at OpenAI due to its ease of use and good performance. --- Why it matters: This matters because it provides researchers with a more accessible and efficient alternative to existing reinforcement learning methods, potentially accelerating progress in areas like robotics and game playing. Source: https://openai.com/index/openai-baselines-ppo