princeton-nlp/XTX
[ICLR 2022 Spotlight] Multi-Stage Episodic Control for Strategic Exploration in Text Games
This project helps AI researchers train and evaluate reinforcement learning agents playing text-based adventure games. It takes a text game environment as input and produces a trained agent capable of strategic exploration and exploitation within that game. The primary users are researchers focused on natural language processing, reinforcement learning, and AI agent development in interactive fiction.
Use this if you are an AI researcher looking to develop and test agents that can strategically navigate and solve complex text-based games.
Not ideal if you are looking for a pre-trained agent for a specific text game or a tool for general natural language understanding outside of interactive fiction.
Stars
15
Forks
2
Language
Python
License
—
Category
Last pushed
Feb 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/princeton-nlp/XTX"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TheShadow29/awesome-grounding
awesome grounding: A curated list of research papers in visual grounding
microsoft/XPretrain
Multi-modality pre-training
TheShadow29/zsgnet-pytorch
Official implementation of ICCV19 oral paper Zero-Shot grounding of Objects from Natural...
TheShadow29/VidSitu
[CVPR21] Visual Semantic Role Labeling for Video Understanding (https://arxiv.org/abs/2104.00990)
zeyofu/BLINK_Benchmark
This repo contains evaluation code for the paper "BLINK: Multimodal Large Language Models Can...