Ben Eysenbach

sac. Soft Actor-Critic

do_good. JavaScript

mnm. Code to accompany the paper "Mismatched No More: Joint Model-Policy Optimization for Model-Based RL"

info_geometry. Code to accompany the paper "The Information Geometry of Unsupervised Reinforcement Learning"

intro-rl. Website for Princeton's undergraduate reinforcement learning course

run_map. Plans runs of a specific length

6.882-LDA. Implementation of Latent Dirichlet Allocation and application to DSPACE@MIT

munkres. Munkres algorithm for Python

slideslive-download. How to download your slideslive video

Packing. How many squares can you fit in a circle?

RandomBytes. Small projects and experiments that don't deserve their own repos

coach. Reinforcement Learning Coach by Intel® AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms

ac-connection. Code to accompany the paper "A Connection between One-Step RL and Critic Regularization in RL"

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

DDO. Reimplementation of Deep Discovery of Options [Fox17]