Transfer in Deep Reinforcement Learning using Knowledge Graphs

2019-08-19 · WS 2019 11 · Prithviraj Ammanabrolu, Mark O. Riedl

Text adventure games, in which players must make sense of the world through text descriptions and declare actions through text descriptions, provide a stepping stone toward grounding action in language. Prior work has demonstrated that using a knowledge graph as a state representation and question-answering to pre-train a deep Q-network facilitates faster control policy transfer. In this paper, we explore the use of knowledge graphs as a representation for domain knowledge transfer for training text-adventure playing reinforcement learning agents. Our methods are tested across multiple computer generated and human authored games, varying in domain and complexity, and demonstrate that our transfer learning methods let us learn a higher-quality control policy faster.

📄 PDF Abstract BibTeX arXiv:1908.06556

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningKnowledge Graphs Question Answering reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Transfer Learning

Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration Under Uncertainty

2021-05-11 · Fanfei Chen, Paul Szenher, Yewei Huang, Jinkun Wang 외

This paper studies the problem of autonomous exploration under localization uncertainty for a mobile robot with 3D range sensing. We present a framework for self-learning a high-performance exploration policy in a single…

Decision Making Deep Reinforcement Learning Domain Adaptation reinforcement-learning+3

An Adversarial Transfer Network for Knowledge Representation Learning

2021-04-30 · Huijuan Wang, Shuangyin Li, Rong pan

Knowledge representation learning has received a lot of attention in the past few years. The success of existing methods heavily relies on the quality of knowledge graphs. The entities with few triplets tend to be learne…

Graph Embedding Knowledge Graph Completion Knowledge Graph Embedding Knowledge Graphs+1

Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning

2025-09-30 · Junhong Lin, Shicheng Liu, Jinyeop Song, Song Wang 외 arxiv

Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs) to reduce hallucination and provide reasoning traces. However, current KG-RA…

Graph Question Answering Reinforcement Learning Knowledge Graphs

Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs

2025-07-09 · Guobin Zhu, Rui Zhou, Wenkang Ji, Hongyin Zhang 외 arxiv

Multi-task multi-agent reinforcement learning (MT-MARL) has recently gained attention for its potential to enhance MARL's adaptability across multiple tasks. However, it is challenging for existing multi-task learning me…

Multi-agent Reinforcement Learning Multi-Task Learning

Augmenting Knowledge Transfer across Graphs

2022-12-09 · Yuzhen Mao, Jianhui Sun, Dawei Zhou

Given a resource-rich source graph and a resource-scarce target graph, how can we effectively transfer knowledge across graphs and ensure a good generalization performance? In many high-impact domains (e.g., brain networ…

Domain Adaptation Transfer Learning