Transfer learning is a conceptually-enticing paradigm in pursuit of truly intelligent embodied
agents. The core concept—reusing prior knowledge to learn in and from novel situations—is …

Recent advancements in reasoning abilities of Large Language Models (LLM) has
promoted their usage in problems that require high-level planning for robots and artificial …

Abstract Despite advances in Reinforcement Learning, many sequential decision making
tasks remain prohibitively expensive and impractical to learn. Recently, approaches that …

Reinforcement Learning (RL) has made significant strides in enabling artificial agents to
learn diverse behaviors. However, learning an effective policy often requires a large number …

This work presents a framework that allows Unmanned Surface Vehicles (USVs) to avoid
dynamic obstacles through initial training on an Unmanned Ground Vehicle (UGV) and …

Multi-agent learning has made significant strides in recent years. Benefiting from deep
learning, multi-agent deep reinforcement learning (MADRL) has transcended traditional …

Despite recent progress in Reinforcement Learning for robotics applications, many tasks
remain prohibitively difficult to solve because of the expensive interaction cost. Transfer …

Advances in reinforcement learning (RL) have enabled robots to learn a wide range of
behaviors. Despite this, scaling the magnitude of learned behaviors to complex sequential …

Emergence of Deep Neural Networks in Reinforcement Learning (RL) have enabled robots
to learn a wide range of behaviors. Despite these advances, in many tasks, the number of …