Hypothesis, Verification, and Induction: Grounding Large Language Models with Self-Driven Skill Learning
DOI:
https://doi.org/10.1609/aaai.v38i13.29376Keywords:
ML: Reinforcement Learning, PRS: Planning with Language Models, NLP: (Large) Language ModelsAbstract
Large language models (LLMs) show their powerful automatic reasoning and planning capability with a wealth of semantic knowledge about the human world. However, the grounding problem still hinders the applications of LLMs in the real-world environment. Existing studies try to fine-tune the LLM or utilize pre-defined behavior APIs to bridge the LLMs and the environment, which not only costs huge human efforts to customize for every single task but also weakens the generality strengths of LLMs. To autonomously ground the LLM onto the environment, we proposed the Hypothesis, Verification, and Induction (HYVIN) framework to automatically and progressively ground the LLM with self-driven skill learning. HYVIN first employs the LLM to propose the hypothesis of sub-goals to achieve tasks and then verify the feasibility of the hypothesis via interacting with the underlying environment. Once verified, HYVIN can then learn generalized skills with the guidance of these successfully grounded subgoals. These skills can be further utilized to accomplish more complex tasks that fail to pass the verification phase. Verified in the famous instruction following task set, BabyAI, HYVIN achieves comparable performance in the most challenging tasks compared with imitation learning methods that cost millions of demonstrations, proving the effectiveness of learned skills and showing the feasibility and efficiency of our framework.Downloads
Published
2024-03-24
How to Cite
Peng, S., Hu, X., Yi, Q., Zhang, R., Guo, J., Huang, D., Tian, Z., Chen, R., Du, Z., Guo, Q., Chen, Y., & Li, L. (2024). Hypothesis, Verification, and Induction: Grounding Large Language Models with Self-Driven Skill Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(13), 14599-14607. https://doi.org/10.1609/aaai.v38i13.29376
Issue
Section
AAAI Technical Track on Machine Learning IV