method · first seen 3 Nov 2026
automated reward and environment design
Using LLMs to generate reinforcement learning environments, reward and MDP formulations automatically.
Mentions per week
PapersCodeDiscussion
Earliest sources
- LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy GenerationPapers · 3 Nov 2026 · Hong Je-Gal, Jinwoo Kim, Chanbin Yi, Hyun-Suk Lee
Latest sources
- LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy GenerationPapers · 3 Nov 2026 · Hong Je-Gal, Jinwoo Kim, Chanbin Yi, Hyun-Suk Lee