anair13

mj_envs

A collection of MuJoCo based environments.

rlkit

Collection of reinforcement learning algorithms

bullet-manipulation-affordances

deon

A utility for managing DEcentralized ONline datasets

mujoco-torch

agents

TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.

anair13.github.io

Personal pages

awr

Implementation of advantage-weighted regression.

bairblog.github.io

BEAR

Code for Stabilizing Off-Policy RL via Bootstrapping Error Reduction

berkeley_sawyer

cs267-hw0

Hosting website for CS 267 (Parallel Computing) HW0

DomainBed

DomainBed is a suite to test domain generalization algorithms

doodad

epicurve

evosoro

A Python Soft Robot Simulator Using Voxelyze

fundvis

Visualisation of Fund Performance

glow

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

implicit_q_learning

kerala-cookbook

metaworld

An open source robotics benchmark for meta- and multi-task reinforcement learning

notebooks

REALCompetitionStartingKit

realnvp

PyTorch implementation of Real NVP

residualrl.github.io

Public website for Residual RL project

RLBench

A large-scale benchmark and learning environment.

robosuite

Surreal Robotics Suite: standardized and accessible robot manipulation benchmark in physics simulation

sawyer_control

Python3 ROS Interface to Rethink Sawyer Robots with OpenAI Gym Compatibility

surreal

Open-Source Distributed Reinforcement Learning Framework by Stanford Vision and Learning Lab

thesis