EdanToledo

Stoix

🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL

JAX-MAML

Super simple implementation of MAML for RL in JAX

RL-Algorithms

Jupyter Notebooks of minimal Reinforcement Learning Algorithms

dreamerv3-1

Mastering Diverse Domains through World Models

EdanToledo

jax-dreamer

Dreamer on JAX

Robotics-3D-Potential-Fields

ai-economist

Foundation is a flexible, modular, and composable framework to model socio-economic behaviors and dynamics with both agents and governments. This framework can be used in conjunction with reinforcement learning to learn optimal economic policies, as done by the AI Economist (https://www.einstein.ai/the-ai-economist).

Basic-NN

Basic Neural Network that uses either a threshold or sigmoid activation function. Nodes use the perceptron learning rule.

clrs

Connect-Four-Against-AlphaZero

Simple hack to existing connect 4 javascript app to allow for AlphaZero model to play online

CSC3022F-Huffman-Encoding

C++ implementation of a huffman tree and encoding - Compress and Decompress text files

CSC3022F-K-Means-Clustering

K means clustering assignment for CSC3022F

L48-Taxation-Analysis

Language-Modelling-Pytorch

N-gram Language Model using PyTorch

dejax

Accelerated replay buffers in JAX

DQN-and-Actor-Critic-PyTorch

Really simple implementation of DQN in pytorch for gym environments

DuelingDDQN-and-AlphaZero

Implementation of DQN, DDQN and Dueling (D)DQN to play Pong. AlphaZero implementation to play Connect4

GridWorldRLModelFree

Model Free TD(λ) implementation for pathfinding in a grid world. Makes use of Q Learning

gymnax

RL Environments in JAX 🌍

IQA

Extensions to Yuan et al. QAit task.

marl-eval

A tool for aggregating and plotting MARL experiment data.

Mava

🦁 A library of multi-agent reinforcement learning systems and components

meltingpot

A suite of test scenarios for multi-agent reinforcement learning.

ModelRenderingOpenGL

Simple OpenGL model rendering with phong shading

PCA

Answering PCA Question Assignment 5

popjym

POPGym Library in JAX

R255-ImitationLearning

REINFORCE-PyTorch

Simple Implementation of REINFORCE and PPO

VectorizedMultiAgentSimulator

VMAS is a vectorized framework designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.