jdmartin86

John D. Martin's repositories

dqn-flax

Implementation of the Deep Q-Network (DQN) using JAX and FLAX.

Language:Python400

lib-mlgp

Most Likely Gaussian Process Library

Language:C++3 1 1

smp

This is a branch of the Sampling-based Motion Planning library

Language:C++3 10

bezier

A library that computes quartic Bézier curves

Language:C2 10

dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

Language:Jupyter NotebookApache-2.01 20

pddlyte

PDDLyte --- A Partial Implementation of The Planning Domain Definition Language

Language:TeX1 10

vc-smc

Language:Jupyter Notebook1 20

2019_jdmartin86_webpage

Professional website

Language:CSSMIT010

2021-naamii-rl-practical

The NAAMII AI Winter School reinforcement learning practical assignment.

Language:Jupyter Notebook010

frogseye

Adapting the Function Approximation Architecture in Online Reinforcement Learning

Language:Python030

CppNumericalSolvers

L-BFGS-B and other optimization implementation in pure C++11 using Eigen

Language:C++MIT020

fglib

factor graph library

Language:PythonMIT010

gym-carla

An OpenAI gym wrapper for CARLA simulator

Language:PythonMIT000

gym-minigrid

Minimalistic gridworld package for OpenAI Gym

Language:PythonApache-2.0000

jdmartin86.github.io

Minimal Jekyll blog styled to resemble the look and layout of Edward Tufte's books

Language:HTMLMIT000

ocaml.org

Implementation of the ocaml.org website.

Language:OCaml000

ompl

The Open Motion Planning Library (OMPL), mirror of:

Language:C++NOASSERTION000

POT

Python Optimal Transport library

Language:PythonMIT010

preethagautam.github.io

Language:HTMLGPL-3.0010

torch7

http://torch.ch

Language:CNOASSERTION010