SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.09597 · ACL · 2022

Perceiving the World: Question-guided Reinforcement Learning for Text-based Games

Ling Chen, Chengqi Zhang, Joey Zhou, Yali Du, Meng Fang, Yunqiu Xu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Text-based games provide an interactive way to study natural language processing. While deep reinforcement learning has shown effectiveness in developing the game playing agent, the low sample efficiency and the large action space remain to be the two major challenges that hinder the DRL from being applied in the real world. In this paper, we address the challenges by introducing world-perceiving modules, which automatically decompose tasks and prune actions by answering questions about the environment. We then propose a two-phase training framework to decouple language learning from reinforcement learning, which further improves the sample efficiency. The experimental results show that the proposed method significantly improves the performance and sample efficiency. Besides, it shows robustness against compound error and limited pre-training data.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2204.09597")
get_code_for_paper("2204.09597")
have("2204.09597")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2204.09597.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2204.09597.svg)](https://syntology.ai/paper/2204.09597)

Connect an agent — have() is free.