jamesborg46

BNN

Bayesian Neural Network written in PyTorch with Epistemic and Aleatoric uncertainty estimates captured in weights and biases

pytorch-dreamerv2

pytorch dreamer v2 implementation

robust_rewards_from_preferences

Comparing IRL methods for efficiency and robustness

aaproject

all things author attribution

akro

Spaces types for reinforcement learning

BayesNN

Implementation of Bayesian Neural Network in TensorfFlow

bullet3

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

cs-video-courses

List of Computer Science courses with video lectures.

dowel

A little logger for machine learning research

dreamerv2

Mastering Atari with Discrete World Models

garage

A toolkit for reproducible reinforcement learning research.

gym

A toolkit for developing and comparing reinforcement learning algorithms.

gym-sokoban

Sokoban environment for OpenAI Gym

jamesborg46.github.io

✨ Build a beautiful and simple website in literally minutes. Demo at https://beautifuljekyll.com

legallm

machine_learning

A repository to practice and learn machine learning

mujoco-py

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

nvim-gdb

Neovim thin wrapper for GDB, LLDB, PDB/PDB++ and BashDB

object_detection

pet_detection

reinforcement-learning

Various RL algorithms based implemented with AI gym

rl-baselines3-zoo

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

rl-teacher

Code for Deep RL from Human Preferences [Christiano et al]. Plus a webapp for collecting human feedback

rlkit

Collection of reinforcement learning algorithms

sac-discrete.pytorch

A PyTorch implementation of SAC-Discrete.

safety-gym

Tools for accelerating safe exploration research.

stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

vae

variational auto-encoder pytorch implementation

varibad

Implementation of VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning - Zintgraf et al. (ICLR 2020)

youtube-8m

Starter code for working with the YouTube-8M dataset.