jannerm

diffuser

Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

mbpo

Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"

trajectory-transformer

Code for the paper "Offline Reinforcement Learning as One Big Sequence Modeling Problem"

ddpo

Code for the paper "Training Diffusion Models with Reinforcement Learning"

intrinsics-network

Code for the paper "Self-Supervised Intrinsic Image Decomposition"

spatial-reasoning

Code for the paper "Representation Learning for Grounded Spatial Reasoning"

gamma-models

Code for the paper "Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction"

o2p2

face-intrinsics

torch-colormap

MATLAB-style colormaps for Torch

bullet-manipulation

Robotic manipulation in PyBullet

slice-sampling

d4rl

A benchmark for offline reinforcement learning.

bairblog.github.io

bullet3

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

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

doodad

gamma-blog

Gumbel_Softmax_VAE

PyTorch implementation of a Variational Autoencoder with Gumbel-Softmax Distribution

gym_minigrid

mbpo-www

mujoco-py

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

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.

rlkit

Collection of reinforcement learning algorithms

SimpleSAC

A simple and easy to use implementation of the soft actor-critic algorithm.

viskit

rllab's viskit with some added features