Projects | MODE Collaboration

Data-Driven Decision-Making Algorithms

Wed, 04 Oct 2023 00:00:00 +0000

A main research direction for the AIR-DREAM Lab is to develop high-performance, robust, generalizable, and real-world deployable data-driven decision-making algorithms. We are specifically interested in offline policy learning methods, such as offline reinforcement learning (RL), offline imitation learning (IL), and offline planning, which enable a simulation-free and low-cost solution to address many real-world problems.

Our current research focus includes:

Sample-efficient / high-generalization offline RL / IL / planning algorithms

Foundation models for decision-making

Safe offline RL algorithms

Hybrid RL that combines offline and online policy learning

Offline policy learning under imperfect reward

Feedback-efficient RLHF

Learning-based Methods for Robotics & Autonomous Driving

Tue, 03 Oct 2023 00:00:00 +0000

We focus on developing robotic control and autonomous driving policy learning methods that could directly learn from real-world data, bypassing or alleviating sim-to-real gap, while achieving robust and generalizable performance.

Our current research focus includes:

Offline RL / IL / planning methods for autonomous driving and robotic control

Offline policy optimization for safety-critical scenarios

Foundation models for robotic control

Sim-to-real adaptation

Latest Achievement

X-VLA has won First Place in the AGIBOT World Challenge (Manipulation track) @ IROS 2025!

Diffusion-Planner: Diffusion-Based Planning for Autonomous Driving with Flexible Guidance

Data-Driven Methods for Sustainable Industrial and AIoT Systems

Mon, 02 Oct 2023 00:00:00 +0000

Conventional industrial systems and emerging systems such as data centers, 5G communication networks consume enormous amount of energy and non-renewable resources. We focus on developing advanced data-driven AI methods to optimize real-world complex industrial and AIoT systems. Helping the related industries to improve operation efficiency, save energy, reduce emission, and ultimately achieving the goal of green and sustainable development.

Our current research focus includes:

Simulator-Free Optimization

Data-driven control optimization for complex industrial systems

Data Center Efficiency

Energy saving optimization for data centers

5G Beamforming

Massive MIMO Beamforming optimization for 5G

Hybrid RL

Engineering policy integrated hybrid reinforcement learning

Latest Achievement

Data Center Cooling System Optimization

Tools & Libraries

Sun, 01 Oct 2023 00:00:00 +0000

We provide open code implementations for most of our research, please check our papers for related codes. In addition, we aim to develop easy-to-use and comprehensive algorithm libraries and tools to accelerate the real-world deployment of advanced data-driven decision-making methods.

Data-Drivien Decision-Making Libraries / Tools

Data-Driven Control Lib (D2C) is a library for data-driven decision-making & control based on state-of-the-art offline reinforcement learning (RL), offline imitation learning (IL), and offline planning algorithms. It is a platform for solving various decision-making & control problems in real-world scenarios. D2C is designed to offer fast and convenient algorithm performance development and testing, as well as providing easy-to-use toolchains to accelerate the real-world deployment of SOTA data-driven decision-making methods.

The current supported offline RL/IL algorithms include (more to come):

Features:

D2C includes a large collection of offline RL and IL algorithms: model-free and model-based offline RL/IL algorithms, as well as planning methods.
D2C is highly modular and extensible. You can easily build custom algorithms and conduct experiments with it.
D2C automates the development process in real-world control applications. It simplifies the steps of problem definition/mathematical formulation, policy training, policy evaluation and model deployment.

Library Information:

The library is available in https://github.com/AIR-DI/D2C.
The tutorials and API documentation are hosted on air-d2c.readthedocs.io.

Online RL Library

OneRL: Event-driven fully distributed reinforcement learning framework proposed in "A Versatile and Efficient Reinforcement Learning Approach for Autonomous Driving" that can facilitate highly efficient policy learning in RL-based tasks.

Features:

Super fast RL training! (15~30min for MuJoCo & Atari on single machine)
State-of-the-art performance
Scheduled and pipelined sample collection
Completely lock-free execution
Fully distributed architecture
Full profiling & overhead identification tools
Online visualization & rendering
Support multi-GPU parallel training
Support exporting trained policy to ONNX for faster inference & deployment