Maze Subgoal
Fresh
Maze navigation subgoal decomposition environment for training LLMs to generate temporally ordered waypoints for offline RL (STO-RL)
- Type
- RL Env
- Capabilities
- Planning
- Runtime
single-turn- License
- unknown
- Size
- v0.8.9
- Published
- Mar 2026
Cite
Notes
Only stored in your browser.