Offline Reinforcement Learning

concepts · 2 notes linked

Related: Sergey Levine · Reinforcement Learning · Distributional Shift · Arxiv · Deep Learning

Notes

• Decisions from Data: How Offline Reinforcement Learning Will Change How We Use ML — Argument for offline RL enabling data-driven end-to-end decision making
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems — Survey of offline RL algorithms learning policies from static datasets without online interaction