**Don't Mask the Environment: Observation Supervision Changes How Agents Explore

**Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL**

> Agent trajectories record what an agent does and what happens next. Yet standard supervised fine-tuning (SFT) applies loss only to agent-authored action tokens, using environment observations as context but not as prediction targets. We ask whether this convention provides the best initialization for subsequent reinforcement learning. We introduce ActObs, which also supervises the observation tokens already present i...

**来源信息**
- **来源**：HuggingFace Daily Papers（社区热门论文）
- **分类**：行业
- **发布时间**：2026-09-18 08:00（北京时间）
- **原文**：[打开原文](https://huggingface.co/papers/2609.20715)