jens321

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

schedules-and-scaling

PufferLib

Simplifying reinforcement learning for complex game environments

gymnax

RL Environments in JAX 🌍

purejaxrl

Really Fast End-to-End Jax RL Implementations

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Samba

Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"

intelligent-go-explore

Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models

xlstm

Official repository of the xLSTM.

pomdp-baselines

Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022

wandb-offline-sync-hook

A convenient way to trigger synchronizations to wandb / Weights & Biases if your compute nodes don't have internet!

nle

The NetHack Learning Environment

Craftax_Baselines

Craftax

(Crafter + NetHack) in JAX. ICML 2024 Spotlight.

diff_history

[arXiv preprint 2024] Official code release accompanying the paper "diff History for Neural Language Agents" (Piterbarg, Pinto, Fergus)

spectral_ssm

il-scaling-in-games

Official code repo of "Scaling Laws for Imitation Learning in NetHack"

sample-factory

High throughput synchronous and asynchronous reinforcement learning

causal-conv1d

Causal depthwise conv1d in CUDA, with a PyTorch interface

lwm

We develop world models that can be adapted with natural language. Intergrating these models into artificial agents allows humans to effectively control these agents through verbal communication.

HIQL

HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)

katakomba

Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)

procthor

🏘️ Scaling Embodied AI by Procedurally Generating Interactive 3D Houses

controllable_agent

The Controllable Agent project trains RL Agents able to optimize any reward function specified in real time, without any further learning or fine-tuning. Training is reward-free and based on the Forward-Backward representation.

VIMA

Official Algorithm Implementation of ICML'23 Paper "VIMA: General Robot Manipulation with Multimodal Prompts"

hihack

[NeurIPS 2023] Official code release accompanying the paper "NetHack is Hard to Hack" (Piterbarg, Pinto, Fergus)

quasimetric-rl

Open source code for paper "Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning" ICML 2023

acme

A library of reinforcement learning components and agents

broken_neural_scaling_laws

Code Release for "Broken Neural Scaling Laws" (BNSL) paper

VIMABench

Official Task Suite Implementation of ICML'23 Paper "VIMA: General Robot Manipulation with Multimodal Prompts"