USC Learning and Interactive Robot Autonomy Lab (LiraLab) develops algorithms for robot learning, safe and efficient human-robot interaction and multi-agent systems. Our mission is to equip robots, or more generally agents powered with artificial intelligence (AI), with the capabilities that will enable them to intelligently learn, adapt to, and influence the humans and other AI agents. We take a two-step approach to this problem. First, machine learning techniques that we develop enable robots to model the behaviors and goals of the other agents by leveraging different forms of information they leak or explicitly provide. Second, these robots interact with the others to achieve online adaptation by leveraging the learned behaviors and goals while making sure this adaptation is beneficial and sustainable.
Recent News
Check out our YouTube channel for latest talks and supplementary videos for our publications.| Aug 7, 2025: | Our paper "Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions" received the "Outstanding Paper Award on Empirical Reinforcement Learning Research" at RLC 2025. |
| Aug 1, 2025: | Our paper titled "ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations" got accepted to the Conference on Robot Learning (CoRL) 2025 as an oral presentation. |
| Jul 10, 2025: | Yutai Zhou has been named a Capital One Fellow! |
| Jun 26, 2025: | Our paper "ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations" received the best paper award among ~50 papers at the "2nd Workshop on Out-of-Distribution Generalization in Robotics" at RSS 2025. It was also nominated for the best paper award at the "Workshop on Learned Robot Representations" at RSS 2025. |
| Jun 15, 2025: |
Our 2 papers got accepted to the 2025 International Conference on Intelligent Robots and Systems (IROS).: - GABRIL: Gaze-Based Regularization for Mitigating Causal Confusion in Imitation Learning - RAILGUN: A Unified Convolutional Policy for Multi-Agent Path Finding Across Different Environments and Tasks |
| See All |