Human can leverage prior experience and learn novel tasks from a handful of
demonstrations. In contrast to offline meta-reinforcement learning, which aims to achieve …

Learning socially-aware motion representations is at the core of recent advances in multi-
agent problems, such as human motion forecasting and robot navigation in crowds. Despite …

In many real-world scenarios, Reinforcement Learning (RL) algorithms are trained on data
with dynamics shift, ie, with different underlying environment dynamics. A majority of current …

Automated industries lead to high quality production, lower manufacturing cost and better
utilization of human resources. Robotic manipulator arms have major role in the automation …

In real-world decision-making tasks, learning an optimal policy without a trial-and-error
process is an appealing challenge. When expert demonstrations are available, imitation …

Function offloading problems play a crucial role in optimizing the performance of
applications in serverless edge computing (SEC). Existing research has extensively …

In multi-objective decision problems, the same state-action pair under different preference
weights between the objectives, constitutes different optimal policies. The introduction of …

Constrained reinforcement learning (CRL), also termed as safe reinforcement learning, is a
promising technique enabling the deployment of RL agent in real-world systems. In this …

We study the theoretical aspects of CLMs (Controllable Language Models) from a bi-
objective optimization perspective. Specifically, we consider the CLMs as an off-policy RL …

Over the past decade, advancements in deep robot learning have enabled robots to acquire
remarkable capabilities. However, these robots often struggle to generalize to new, unseen …