rlcard
★ 3.6k·MIT·Updated 2024-06-26
RLCard is a toolkit designed for Reinforcement Learning in card games, providing multiple card environments with easy-to-use interfaces. Its goal is to bridge reinforcement learning and imperfect information games, supporting various RL and searching algorithms.
#Reinforcement Learning#Card Games#Imperfect Information Games#Python#Deep Learning#Coding
01
Features
01Provides multiple card game environments for research and development.
02Offers easy-to-use interfaces for implementing various reinforcement learning and search algorithms.
03Supports popular algorithms such as Deep Q-Learning (DQN), NFSP, CFR, and Deep Monte-Carlo (DMC).
04Integrates with PettingZoo and provides PyTorch implementations for training algorithms.
05Includes human interfaces for interactive play and a GUI demo (RLCard-Showdown) for visualization.
02
Compatibility
PyTorch
PyTorch Support
Verified via docs
PettingZoo
PettingZoo Integration
Verified via docs
Jupyter Notebook
Jupyter Tutorials
Verified via docs
R
R Language (via Reticulate)
Verified via docs
Conda
Conda Package
Verified via docs
03
Quick start
1
$ pip3 install rlcard
04
Use cases
↳Developing and testing reinforcement learning agents for various card games.
↳Conducting research into strategies and algorithms within imperfect information game environments.
↳Comparing the performance and effectiveness of different RL and search algorithms.
05
Alternatives
verl-agent★ 2.4k
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
ir-sim★ 1.1k
A Python-based lightweight robot simulator designed for navigation, control, and reinforcement learning
skrl★ 1.1k
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments
MAgent★ 1.8k
MAgent is a research platform for many-agent reinforcement learning (AAAI 2018 demo). No longer maintained; the maintained fork is Farama Foundation's MAgent2.
code-act★ 1.7k
Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.
Comments
Log in to leave a comment
No comments yet. Be the first!