An elegant PyTorch deep reinforcement learning library.

Baseline model for "GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping" (CVPR 2020)

Reproduction of self-play described in paper "Emergent Complexity via Multi-Agent Competition", adapted from PPO2 implementation in OpenAI baselines.

An implementation of Q-Learning RL Algorithm. The algorithm is built around a game of snake and the game's grid basis made it ideal for implementation of a state configuration.

Source files for my course on Game Theory.

grasp labels auto-annotation

[CVPR 2022] Pre-Training 3D Point Cloud Transformers with Masked Point Modeling

Implementation of 6-DoF GraspNet with tensorflow and python. This repo has been tested with python 2.7 and tensorflow 1.12.

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

A toolkit for discourse segmentation (EDU segmentation).

Python code written for MIT's Machine Learning course offered on edX

scikit-learn: machine learning in Python

Self-contained implementation of non-convex optimization algorithms in python. Steepest Descent, Conjugate Gradient, Newton's Method, Quasi-newton (BFGS), l-BFGS

Batch running text-based games in Frotz