The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…

HOVER

A Reinforcement Learning Project using PPO + Transformer

An RL-Friendly Vision-Language Model for Minecraft

Clean baseline implementation of PPO using an episodic TransformerXL memory

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

Implementation of the transformer from the paper: "Real-World Humanoid Locomotion with Reinforcement Learning"

This repo is a live list of papers on game playing and large multimodality model - "A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges".

[NeurIPS 2023 FMDM Workshop] Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks

Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation (AAAI 2022)

Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation (AAAI 2022)

SMAC: The StarCraft Multi-Agent Challenge

Open-source simulator for autonomous driving research.

GPT-For-NLG-Tasks

DGN Code

A Python wrapper/interface for the fastfusion algorithm