WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?

🌎💪 BrowserGym, a Gym environment for web task automation

GFlowNet library

Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!

AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

A differentiable physics engine and multibody dynamics library for control and robot learning.

An elegant PyTorch deep reinforcement learning library.

A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

Optax is a gradient processing and optimization library for JAX.

Simple and easily configurable grid world environments for reinforcement learning

SAPIEN Manipulation Skill Framework, a GPU parallelized robotics simulator and benchmark

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge)

An offline deep reinforcement learning library

Scripts to recreate the D4RL datasets with Minari

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools.

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

Gym for multi-agent reinforcement learning

A small and fast image rescaling library with SIMD support

Easy-to-use micro-wrappers for Gym and PettingZoo based RL Environments

A standard API for reinforcement learning and a diverse set of reference environments (formerly Gym)

Run pytest on markdown code fence blocks

🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.