playing-games-2

text-based games

3260 papers • 126 benchmarks • 313 datasets

Text-based games to evaluate the Reinforcement Learning Agents

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in text-based-games-2

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find text-based-games-2 models and implementations

matthewsparr/Deep-Zork

3 papers 19

Datasets

Jericho

TextWorld KG

Cards Against Humanity

Subtasks

No subtasks available.

Most implemented papers

Language Understanding for Text-based Games using Deep Reinforcement Learning

R. Barzilay, Tejas D. Kulkarni, Karthik Narasimhan•Sun Jun 28 2015

This paper employs a deep reinforcement learning framework to jointly learn state representations and action policies using game rewards as feedback to map text descriptions into vector representations that capture the semantics of the game states.

377

Content

0

Paper Graph

Deep Reinforcement Learning with a Natural Language Action Space

L. Deng, Jianfeng Gao, Xiaodong He, Mari Ostendorf, Jianshu Chen, Lihong Li, Ji He•Fri Nov 13 2015

This paper introduces a novel architecture for reinforcement learning with deep neural networks designed to handle state and action spaces characterized by natural language, as found in text-based games, called a deep reinforcement relevance network (DRRN).

258 0

Paper Graph

Using reinforcement learning to learn how to play text-based games

Mikuláš Zelinka•Fri Jan 05 2018

This work presents a general text game playing agent, testing its generalisation and transfer learning performance and showing its ability to play multiple games at once, and presents pyfiction, an open-source library for universal access to different text games that could serve as a baseline for future research.

13 0

Paper Graph

Counting to Explore and Generalize in Text-based Games

Adam Trischler, Alessandro Sordoni, Rémi Tachet des Combes, Matthew J. Hausknecht, Xingdi Yuan, Marc-Alexandre Côté, R. Laroche•Thu Jun 28 2018

A recurrent RL agent with an episodic exploration mechanism that helps discovering good policies in text-based game environments and observes that the agent learns policies that generalize to unseen games of greater difficulty.

75 0

Paper Graph

Towards Solving Text-based Games by Producing Adaptive Action Spaces

Xingdi Yuan, Marc-Alexandre Côté, Layla El Asri, Ruo Yu Tao•Sun Dec 02 2018

This work proposes to tackle the first task and train a model that generates the set of all valid commands for a given context and tries three generative models on a dataset generated with Textworld.

14 0

Paper Graph

TextWorldExpress: Simulating Text Games at One Million Steps Per Second

Marc-Alexandre Côté, Peter Alexander Jansen•Sun Jul 31 2022

This work presents TextWorldExpress, a high-performance simulator that includes implementations of three common text game benchmarks that increases simulation throughput by approximately three orders of magnitude, reaching over one million steps per second on common desktop hardware.

10 0

Paper Graph

Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines

Kartik Talamadupula, Mrinmaya Sachan, K. Murugesan, Murray Campbell, G. Tesauro, Mattia Atzeni, Pavan Kapanipathi, Pushkar Shukla, Sadhana Kumaravel•Wed Oct 07 2020

This paper designs a new text-based gaming environment called TextWorld Commonsense (TWC) for training and evaluating RL agents with a specific kind of commonsense knowledge about objects, their attributes, and affordances, and shows that agents which incorporate Commonsense knowledge in TWC perform better, while acting more efficiently.

60 0

Paper Graph

Constructing Temporal Dynamic Knowledge Graphs from Interactive Text-based Games

Keunwoo Peter Yu•Thu Nov 02 2023

The Temporal Discrete Graph Updater (TDGU), a novel neural network model that represents dynamic knowledge graphs as a sequence of timestamped graph events and models them using a temporal point based graph neural network, is proposed and shown to outperforms the baseline DGU.

1 0

Paper Graph

TextWorld: A Learning Environment for Text-based Games

Adam Trischler, Matthew J. Hausknecht, Xingdi Yuan, Marc-Alexandre Côté, Ákos Kádár, Layla El Asri, B. Kybartas, Tavian Barnes, Emery Fine, James Moore, Mahmoud Adada, Wendy Tay•Thu Jun 28 2018

TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like state tracking and reward assignment, and comes with a curated list of games whose features and challenges the authors have analyzed.

433 0

Paper Graph

Building Dynamic Knowledge Graphs from Text-based Games

Adam Trischler, Xingdi Yuan, Marc-Alexandre Côté, Mikuláš Zelinka, R. Laroche•Sun Oct 20 2019

This preliminary work proposes a novel Sequence-to-Sequence (Seq2Seq) architecture to generate elementary KG operations and introduces a new dataset for KG extraction built upon text-based game transitions.

12 0

Paper Graph

Adding a benchmark result helps the community track progress.