LAMDA-RL Lab is at the forefront of advancing the field of reinforcement learning and its application to creating general decision-making intelligence, by pushing the boundaries of what's possible with RL techniques.
We focus on developing novel algorithms and architectures that enable RL systems to learn and make decisions in increasingly general and adaptable ways. Some key areas we are exploring include:
- Imitation learning;
- Offline reinforcement learning;
- Model-based RL and world model learning;
- Multi-agent and collaborative RL;
- Planning and learning with large models.
Through both fundamental and application research, our aim is to create RL-based systems that exhibit truly intelligent and general decision-making capabilities. For more information about our lab and research, please refer to our website https://lamda-rl.nju.edu.cn/.
