色婷婷色综合,亚洲天堂2014,亚洲精品2区,亚洲午夜一区二区

<返回

True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement Learning

Weihao Tan, Wentao Zhang, Shanqi Liu, Longtao Zheng, Xinrun Wang, Bo An

ICLR 2024 Conference

May 2024

Keywords: Reinforcement Learning, Large Language Models, Parameter-Efficient Fine-Tuning

Abstract:

Despite the impressive performance across numerous tasks, large language models (LLMs) often fail in solving simple decision-making tasks due to the misalignment of the knowledge in LLMs with environments. On the contrary, reinforcement learning (RL) agents learn policies from scratch, which makes them always align with environments but difficult to incorporate prior knowledge for efficient explorations. To narrow the gap, we propose TWOSOME, a novel general online framework that deploys LLMs as decision-making agents to efficiently interact and align with embodied environments via RL without requiring any prepared datasets or prior knowledge of the environments. Firstly, we query the joint probabilities of each valid action with LLMs to form behavior policies. Then, to enhance the stability and robustness of the policies, we propose two normalization methods and summarize four prompt design principles. Finally, we design a novel parameter-efficient training architecture where the actor and critic share one frozen LLM equipped with low-rank adapters (LoRA) updated by PPO. We conduct extensive experiments to evaluate TWOSOME. i) TWOSOME exhibits significantly better sample efficiency and performance compared to the conventional RL method, PPO, and prompt tuning method, SayCan, in both classical decision-making environment, Overcooked, and simulated household environment, VirtualHome. ii) Benefiting from LLMs open-vocabulary feature, TWOSOME shows superior generalization ability to unseen tasks. iii) Under our framework, there is no significant loss of the LLMs original ability during online PPO finetuning.

View More PDF>>

主站蜘蛛池模板: 教育| 获嘉县| 新营市| 苍梧县| 长葛市| 凤庆县| 赣州市| 大化| 甘谷县| 远安县| 大悟县| 汉中市| 托克托县| 珲春市| 绥滨县| 井研县| 福海县| 安康市| 和硕县| 齐河县| 白河县| 汽车| 新昌县| 建水县| 桂平市| 曲周县| 江北区| 竹北市| 新疆| 无锡市| 故城县| 湘潭市| 三明市| 镇安县| 柏乡县| 宜春市| 新郑市| 新邵县| 泽库县| 曲水县| 栖霞市|