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

10/22/2020
by   Yunqiu Xu, et al.
0

We study reinforcement learning (RL) for text-based games, which are interactive simulations in the context of natural language. While different methods have been developed to represent the environment information and language actions, existing RL agents are not empowered with any reasoning capabilities to deal with textual games. In this work, we aim to conduct explicit reasoning with knowledge graphs for decision making, so that the actions of an agent are generated and supported by an interpretable inference procedure. We propose a stacked hierarchical attention mechanism to construct an explicit representation of the reasoning process by exploiting the structure of the knowledge graph. We extensively evaluate our method on a number of man-made benchmark games, and the experimental results demonstrate that our method performs better than existing text-based agents.

READ FULL TEXT

page 20

page 26

page 28

page 33

page 34

page 35

page 36

page 39

research
09/21/2021

Generalization in Text-based Games via Hierarchical Reinforcement Learning

Deep reinforcement learning provides a promising approach for text-based...
research
01/23/2020

Graph Constrained Reinforcement Learning for Natural Language Action Spaces

Interactive Fiction games are text-based simulations in which an agent i...
research
05/08/2023

Knowledge-enhanced Agents for Interactive Text Games

Communication via natural language is a crucial aspect of intelligence, ...
research
08/19/2019

Transfer in Deep Reinforcement Learning using Knowledge Graphs

Text adventure games, in which players must make sense of the world thro...
research
06/17/2021

Learning Knowledge Graph-based World Models of Textual Environments

World models improve a learning agent's ability to efficiently operate i...
research
04/08/2023

DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning

Temporal knowledge graphs (TKGs) model the temporal evolution of events ...
research
01/21/2022

Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning

We present a two-step hybrid reinforcement learning (RL) policy that is ...

Please sign up or login with your details

Forgot password? Click here to reset