TextWorld

Learning platform

An environment and tools for training reinforcement learning agents on text-based games

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

GitHub

1k stars
40 watching
186 forks
Language: Jupyter Notebook
last commit: almost 2 years ago
Linked from 1 awesome list

reinforcement-learningtext-based-adventuretext-based-game

Backlinks from these awesome lists:

Related projects:

RepositoryDescriptionStars
nadavbh12/retro-learning-environmentA framework for training AI algorithms using game consoles as input185
taw/imba-game-of-lifeA Game of Life implementation in Imba, using its core language to create a simulation of Conway's Game of Life.7
google-deepmind/spriteworldAn environment designed to test and train reinforcement learning algorithms in a flexible, procedurally generated 2D space with various objects and interactions.369
tatsu-lab/alpaca_farmA framework for simulating and evaluating reinforcement learning from human feedback methods786
robrix/starlightA game project that simulates spaceships in space using Haskell and OpenGL.72
utilforever/robotchessAn Auto Chess simulator built with C++ and reinforcement learning algorithms4
rossjrw/rossjrwA massively multiplayer board game implemented as an asynchronous web application203
drwhut/tabletop-clubAn open-source platform for playing tabletop games in a physics-based 3D environment using the Godot Engine.1,306
stanfordvl/igibsonA simulation environment for training robots to interact with realistic 3D scenes and perform tasks such as navigation and manipulation.676
taw/imba-rotnAn application built with Imba and JavaScript that simulates the ROT-N feature of a fictional game.0
jujuadams/scribbleA text rendering engine for GameMaker that supports multiple effects and internationalization343
sentdex/carla-rlA Reinforcement Learning project for training an autonomous driving agent in a simulated environment using the Carla game engine368
litanlitudan/skyagiA tool for simulating human-like behaviors in language models using generative agents764
microsoft/cyberbattlesimAn experimentation platform to investigate the interaction of automated agents in abstract simulated network environments.1,670
mathworks-robotics/robotics-playgroundA collection of virtual environments designed to teach robotics concepts through interactive simulations.42