With the widespread adoption of deep learning, reinforcement learning (RL) has
experienced a dramatic increase in popularity, scaling to previously intractable problems …

Abstract Offline Reinforcement Learning (RL) has shown promising results in learning a task-
specific policy from a fixed dataset. However, successful offline RL often relies heavily on the …

The robustness of legged locomotion is crucial for quadrupedal robots in challenging
terrains. Recently, Reinforcement Learning (RL) has shown promising results in legged …

In reinforcement learning, the optimism in the face of uncertainty (OFU) is a mainstream
principle for directing exploration towards less explored areas, characterized by higher …

In offline actor–critic (AC) algorithms, the distributional shift between the training data and
target policy causes optimistic value estimates for out-of-distribution (OOD) actions. This …

Offline reinforcement learning (RL), which operates solely on static datasets without further
interactions with the environment, provides an appealing alternative to learning a safe and …

Knowledge distillation (KD) has been widely adopted to compress large language models
(LLMs). Existing KD methods investigate various divergence measures including the …

In autonomous driving, behavioral decision-making and trajectory planning remain huge
challenges due to the large amount of uncertainty in environments and complex interaction …

In deregulated electricity markets, accurate and reliable day-ahead electricity price
forecasting (EPF) is beneficial for hedging volatility risks, implementing dispatch controls …

Reliable interval forecasting of uncertain load with cyberattacks is critical for grid resilience
and decision-making. Nevertheless, various constraints on the predictive distribution …