论文速读记录 | 2025.02

---

目录

• SEABO: A Simple Search-Based Method for Offline Imitation Learning
• Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions
• Training Agents using Upside-Down Reinforcement Learning
• All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL

---

SEABO: A Simple Search-Based Method for Offline Imitation Learning

• arxiv：https://arxiv.org/abs/2402.03807
• GitHub：https://github.com/dmksjfl/SEABO
• 来源：有可能是师兄的新文章，ICLR 2024。
• 主要内容：

Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions

• arxiv：https://arxiv.org/abs/1912.02875
• 来源：曾经感兴趣的 upside down RL。
• 主要内容：

Training Agents using Upside-Down Reinforcement Learning

• arxiv：https://arxiv.org/abs/1912.02877
• 来源：曾经感兴趣的 upside down RL。
• 主要内容：

All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL

• arxiv：https://arxiv.org/abs/2202.11960
• 来源：好像也是关于 upside down RL。
• 主要内容：