ethanluoyc

magi

Reinforcement learning library in JAX.

corax

Corax: Core RL in JAX

optimal_transport_reward

lxm3

LXM3: XManager launch backend for HPC clusters

d4rl-slim

A tiny package for working with D4RL datasets without D4RL.

jam

Jam - JAX models

orax

alfworld

ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

chumpy

d4rl

A benchmark for offline reinforcement learning.

dm-haiku

JAX-based neural network library

dm_env_wrappers

Standalone library of frequently-used wrappers for dm_env environments.

envpool

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

KinPoly

Official implementation of NeurIPS 2021 paper: "Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation". This repo contains a copy of the code for "Universal Humanoid Controller" and "Kinematic Policy".

launchpad

mj_envs

A collection of MuJoCo based environments.

MoCapAct

A Multi-Task Dataset for Simulated Humanoid Control

mujoco-py

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

orbax

Orbax provides common utility libraries for JAX users.

pdm

A modern Python package and dependency manager supporting the latest PEP standards

pybind11_abseil_gh12_repro

reverb

Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research

rlax

rules_python

Bazel Python Rules

SmartPlay

SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. SmartPlay is designed to be easy to use, and to support future development of LLMs.

TextWorld

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

torchrec

Pytorch domain library for recommendation systems

UniversalHumanoidControl

Official Implementation of the Universal Humanoid Controller in Mujoco. Supports Kinpoly (NeurIPS 2021) and EmbodiedPose (NeurIPS 2022).

webarena

Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"