Transfer in Deep Reinforcement Learning using Knowledge Graphs

08/19/2019
by   Prithviraj Ammanabrolu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/04/2018

Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning

Text-based adventure games provide a platform on which to explore reinfo...
research
10/22/2020

Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games

We study reinforcement learning (RL) for text-based games, which are int...
research
08/01/2017

Deep Transfer in Reinforcement Learning by Language Grounding

In this paper, we explore the utilization of natural language to drive t...
research
05/08/2023

Knowledge-enhanced Agents for Interactive Text Games

Communication via natural language is a crucial aspect of intelligence, ...
research
04/23/2018

Towards Symbolic Reinforcement Learning with Common Sense

Deep Reinforcement Learning (deep RL) has made several breakthroughs in ...
research
01/18/2014

Learning to Win by Reading Manuals in a Monte-Carlo Framework

Domain knowledge is crucial for effective performance in autonomous cont...
research
01/19/2021

Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning

In this paper, we consider the problem of leveraging textual description...

Please sign up or login with your details

Forgot password? Click here to reset