6 accepted papers
Large Language Models (LLMs) exhibit strong potential in mathematical reasoning, yet their effectiveness is often limited by a shortage of high-quality queries. This limitation necessitates scaling up computational responses through self-generated data, yet current methods struggle due to spurious c…
Reinforcement learning (RL) has achieved remarkable success in complex robotic systems (eg. quadruped locomotion). In previous works, the RL-based controller was typically implemented as a single neural network with concatenated observation input. However, the corresponding learned policy is highly
Reinforcement learning often suffer from the sparse reward issue in real-world robotics problems. Learning from demonstration (LfD) is an effective way to eliminate this problem, which leverages collected expert data to aid online learning. Prior works often assume that the learning agent and the ex…
Being able to discover diverse useful skills without external reward functions is beneficial in reinforcement learning research. Previous unsupervised skill discovery approaches mainly train different skills in parallel. Although impressive results have been provided, we found that parallel training…
We study two user demands that are important during the exploitation of explanations in practice: 1) understanding the overall model behavior faithfully with limited cognitive load and 2) predicting the model behavior accurately on unseen instances. We illustrate that the two user demands correspond…
Learning user representation is a critical task for recommendation systems as it can encode user preference for personalized services. User representation is generally learned from behavior data, such as clicking interactions and review comments. However, for less popular domains, the behavior data…