长时程 Q-learning 突破 RL 扩展瓶颈
Scaling RL to long horizons remains a major challenge.
AI 导读
将强化学习扩展到长时程仍然是一个重大挑战。 长时程 Q-learning（LQL）通过限制长时程上的价值差异，防止了复合自举误差。 与 1 步 TD 和 n 步回报相比，它显示出巨大提升！
查看原帖In RL, what if we could learn from any experience from any policy in a way that is reliable and scalable? This would be helpful in domains like robotics where new data is expensive. We introduce Long-horizon Q-learning (LQL) to tackle this https://t.co/1Ckb5ZePyo.
正文
当前显示原文，中文全文译文尚未就绪。
Scaling RL to long horizons remains a major challenge.
Long-horizon Q-learning (LQL) prevents compounding bootstrapping errors by bounding the difference in value over long horizons.
It shows large gains over 1-step TD and n-step returns!