Online Planning for Interactive-POMDPs using Nested Monte Carlo Tree Search

Schwartz, Jonathon; Zhou, Ran; Kurniawati, Hanna

doi:10.1109/iros47612.2022.9981713

Cited by 2 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where 𝜂 is a normalizing constant. POMDPs can be solved by many algorithms, such as Grid-based algorithms [72], Monte Carlo tree search [134]. However, due to its partial observability of the environment, POMDPs are more challenging to solve than MDPs.…”

Section: Reinforcement Learning Methodsmentioning

confidence: 99%

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks (GNNs) have emerged as a powerful tool for graph representation learning, in an end-to-end supervised setting, their performance heavily relies on a large amount of task-specific supervision. To reduce labeling requirement, the "pre-train, fine-tune" and "pre-train, prompt" paradigms have become increasingly common. In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner. However, existing study of prompting on graphs is still limited, lacking a universal treatment to appeal to different downstream tasks. In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs. GraphPrompt not only unifies pre-training and downstream tasks into a common task template, but also employs a learnable prompt to assist a downstream task in locating the most relevant knowledge from the pre-trained model in a task-specific manner. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt. CCS CONCEPTS• Computing methodologies → Learning latent representations; • Information systems → Data mining.

show abstract

Section: Reinforcement Learning Methodsmentioning

confidence: 99%