Flow RL

Flow RL is a high-performance reinforcement learning library, combining modern deep RL algorithms with flow and diffusion models for advanced policy parameterization, planning ability or dynamics modeling. It features:

• State-of-the-Art Algorithms and Efficiency: We provide JAX implementations of SOTA algorithms, such FQL, BDPO, DAC and etc;
• Flexible Flow Architectures: We provide built-in support various types of flow and diffusion models, such as CNFs and DDPM;
• Comprehensive Evaluations: We test the algorithms on commonly adopted benchmark and provide the results.

🚀 Installation & Usage

Currently FlowRL is hosted on PyPI and therefore can be installed via pip install flowrl. However, we recommend to clone and install the library using the following commands:

git clone https://github.com/typoverflow/flow-rl.git
cd flow-rl
pip install -e .

Alternatively, you can use our Docker image:

docker pull typoverflow/flow-rl
docker run --gpus all -it typoverflow/flow-rl bash

The entry files are presented in examples/. Please refer to the scripts in scripts/ for how to execute the algorithms.

📊 Supported Algorithms

Offline RL:

Algorithm	Location	WandB Report
IQL	flowrl/agent/iql.py	[Performance] [Full Log]
IVR	flowrl/agent/ivr.py	[Performance] [Full Log]
FQL	flowrl/agent/fql/fql.py	[Performance] [Full Log]
DAC	flowrl/agent/dac.py	[Performance] [Full Log]
BDPO	flowrl/agent/bdpo/bdpo.py	[Performance] [Full Log]

Online RL (Gym-MuJoCo):

Algorithm	Location	WandB Report
SAC	flowrl/agent/online/sac.py	[Full Log]
TD3	flowrl/agent/online/td3.py	[Full Log]
SDAC	flowrl/agent/online/sdac.py	[Full Log]

📝 Citing Flow RL

If you use Flow RL in your research, please cite:

@software{flow_rl,
  author       = {Chen-Xiao Gao and Mingjun Cao},
  title        = {Flow RL: Flow-based Reinforcement Learning Algorithms},
  year         = 2025,
  version      = {v0.0.1},
  url          = {https://github.com/typoverflow/flow-rl}
}

💎 Acknowledgements

Inspired by foundational work from

• Jax-CORL
• DAC