4 papers
Unified Number-Free Text-to-Motion Generation Via Flow Matching
Guanhe Huang, Oya Celiktutan
Generative models excel at motion synthesis for a fixed number of agents but struggle to generalize with variable agents. Based on limited, domain-specific data, existing methods e…
Efficient Continual Adaptation of Pretrained Robotic Policy with Online Meta-Learned Adapters
Ruiqi Zhu, Endong Sun, Guanhe Huang +1
Continual adaptation is essential for general autonomous agents. For example, a household robot pretrained with a repertoire of skills must still adapt to unseen tasks specific to…
Cross Domain Policy Transfer with Effect Cycle-Consistency
Ruiqi Zhu, Tianhong Dai, Oya Celiktutan
Training a robotic policy from scratch using deep reinforcement learning methods can be prohibitively expensive due to sample inefficiency. To address this challenge, transferring…
Learning to Solve Tasks with Exploring Prior Behaviours
Ruiqi Zhu, Siyuan Li, Tianhong Dai +2
Demonstrations are widely used in Deep Reinforcement Learning (DRL) for facilitating solving tasks with sparse rewards. However, the tasks in real-world scenarios can often have va…