Timezone: »

 
Poster
WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
Shunyu Yao · Howard Chen · John Yang · Karthik Narasimhan

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #1040
in Poster Session 5 »

Most existing benchmarks for grounding language in interactive environments either lack realistic linguistic elements, or prove difficult to scale up due to substantial human involvement in the collection of data or feedback signals. We develop WebShop – a simulated e-commerce website environment with 1.18 million real-world products and 12,087 crowd-sourced text instructions. In this environment, an agent needs to navigate multiple types of webpages and issue diverse actions to find, customize, and purchase a product given an instruction. WebShop provides several challenges including understanding compositional instructions, query (re-)formulation, dealing with noisy text in webpages, and performing strategic exploration. We collect over 1,600 human trajectories to first validate the benchmark, then train and evaluate a diverse range of agents using reinforcement learning, imitation learning, and pre-trained image and language models. Our best model achieves a task success rate of 29%, which significantly outperforms rule heuristics but is far lower than expert human performance (59%). We also analyze agent and human trajectories and ablate various model components to provide insights for developing future agents with stronger language understanding and decision making abilities. Finally, we show our agent trained on WebShop exhibits non-trivial sim-to-real transfer when evaluated on amazon.com and ebay.com, indicating the potential value of our benchmark for developing practical web agents that can operate in the wild.

Keywords: Natural Language Processing · Reinforcement Learning · imitation learning · web tasks · sim-to-real transfer · language grounding
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Shunyu Yao (Princeton University)
Howard Chen (Princeton University)
John Yang (Princeton University)
John Yang

I'm a 2nd year Master's student studying Natural Language Processing at Princeton University, advised by Professor Karthik Narasimhan.

Karthik Narasimhan (Princeton University)

More from the Same Authors