The reviewed record of science sign in
Pith

arxiv: 2107.08408 · v2 · pith:2ZNIFROY · submitted 2021-07-18 · cs.CL · cs.AI· cs.MA· cs.RO

Pre-trained Language Models as Prior Knowledge for Playing Text-based Games

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:2ZNIFROYrecord.jsonopen to challenge →

classification cs.CL cs.AIcs.MAcs.RO
keywords gamesagentslanguagemodelstextualapproachesenoughenvironment
0
0 comments X
read the original abstract

Recently, text world games have been proposed to enable artificial agents to understand and reason about real-world scenarios. These text-based games are challenging for artificial agents, as it requires an understanding of and interaction using natural language in a partially observable environment. Agents observe the environment via textual descriptions designed to be challenging enough for even human players. Past approaches have not paid enough attention to the language understanding capability of the proposed agents. Typically, these approaches train from scratch, an agent that learns both textual representations and the gameplay online during training using a temporal loss function. Given the sample-inefficiency of RL approaches, it is inefficient to learn rich enough textual representations to be able to understand and reason using the textual observation in such a complicated game environment setting. In this paper, we improve the semantic understanding of the agent by proposing a simple RL with LM framework where we use transformer-based language models with Deep RL models. We perform a detailed study of our framework to demonstrate how our model outperforms all existing agents on the popular game, Zork1, to achieve a score of 44.7, which is 1.6 higher than the state-of-the-art model. Overall, our proposed approach outperforms 4 games out of the 14 text-based games, while performing comparable to the state-of-the-art models on the remaining games.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. In Context Learning and Reasoning for Symbolic Regression with Large Language Models

    cs.CL 2024-10 unverdicted novelty 5.0

    GPT-4 models rediscover Langmuir isotherms and produce fits on Nikuradse pipe-flow data via iterative chain-of-thought prompting with scientific context and external code feedback.

  2. Remember what you did so you know what to do next

    cs.CL 2023-10 unverdicted novelty 5.0

    GPT-J with full action history achieves 3.5x improvement over RL in ScienceWorld and matches a two-stage system using 29x larger models.