Skip to content
/ MRIC Public

MRIC: Model-Based Reinforcement-Imitation Learning with Mixture-of-Codebooks for Autonomous Driving Simulation

Notifications You must be signed in to change notification settings

TimHo0331/MRIC

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

25 Commits
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

MRIC πŸ›£οΈ

Model-Based Reinforcement-Imitation Learning with Mixture-of-Codebooks for Autonomous Driving Simulation

MRIC Framework

arXiv Status: Under Review License: MIT


✨ Highlights

  • Gradient Highway + Inter-Agent Pathways for efficient credit assignment
  • Dual Regularisation: open-loop IL stabilisation & model-based RL safety constraints
  • Mixture-of-Codebooks with temporal abstraction to capture multi-modal behaviour
  • State-of-the-art performance on the large-scale Waymo Open Motion Dataset

Note: Full source code, trained models and experiment scripts will be released once the paper is formally accepted.


πŸ“¦ Repository Structure

mric/
β”œβ”€ docs/
β”‚  β”œβ”€ figs/            # architecture.png
β”‚  └─ gifs/            # demo_lane_change.gif, …
β”œβ”€ mric/               # core library (to be released)
β”œβ”€ examples/           # training / evaluation scripts
└─ README.md

πŸ”§ Installation

# Clone with submodules if any
git clone --recursive https://github.com/your-org/mric.git
cd mric

# (Optional) Create environment
conda create -n mric python=3.10
conda activate mric

# Install dependencies
pip install -r requirements.txt

πŸš€ Quick Start

# 1. Download Waymo Open Motion Dataset (WOMD) and set DATA_ROOT
export DATA_ROOT=/path/to/womd

# 2. Train MRIC
python examples/train_mric.py --config configs/mric_womd.yaml

# 3. Evaluate
python examples/eval_mric.py --checkpoint checkpoints/mric_best.pth

πŸŽ₯ Demos

Lane-change Intersection Emergent

Scenario GIF Path
Highway lane-change docs/gifs/demo_lane_change.gif
Urban intersection docs/gifs/demo_intersection.gif
Emergent behaviour docs/gifs/demo_emergent.gif

πŸ–ΌοΈ Framework Figure

The high-resolution framework diagram lives at docs/figs/architecture.png and is displayed above.


πŸ“„ Citation

@article{he2024mric,
  title   = {MRIC: Model-Based Reinforcement-Imitation Learning with Mixture-of-Codebooks for Autonomous Driving Simulation},
  author  = {Baotian He and Yibing Li},
  journal = {arXiv preprint arXiv:2404.18464},
  year    = {2024}
}

🀝 Contributing

We welcome pull requests once the codebase is public.
Before opening an issue, please search existing ones and read CONTRIBUTING.md.


πŸ“« Contact

For questions, please open a GitHub issue or email
Baotian He Β· hbt18@mails.tsinghua.edu.cn
Yibing Li Β· liyb@tsinghua.edu.cn


Β© 2024-present The MRIC Authors. Released under the MIT License.

About

MRIC: Model-Based Reinforcement-Imitation Learning with Mixture-of-Codebooks for Autonomous Driving Simulation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published