An Analysis of Deep Reinforcement Learning Agents for Text-based Games

TL;DR

This paper evaluates deep reinforcement learning agents in text-based games, focusing on performance analysis, standardized environments, and evaluation methods to improve agent design and benchmarking.

Contribution

It introduces a standardized TBG agent without hand-crafted rules, categorizes evaluation types, and analyzes method performance in a controlled environment.

Findings

Constructed a rule-free standardized TBG agent

Categorized TBG evaluation types

Analyzed method performance in the environment

Abstract

Text-based games(TBG) are complex environments which allow users or computer agents to make textual interactions and achieve game goals.In TBG agent design and training process, balancing the efficiency and performance of the agent models is a major challenge. Finding TBG agent deep learning modules' performance in standardized environments, and testing their performance among different evaluation types is also important for TBG agent research. We constructed a standardized TBG agent with no hand-crafted rules, formally categorized TBG evaluation types, and analyzed selected methods in our environment.