Reinforcement Learning (RL) has emerged as a highly effective technique for addressing
various scientific and applied problems. Despite its success, certain complex tasks remain …

Learning modular structures which reflect the dynamics of the environment can lead to better
generalization and robustness to changes which only affect a few of the underlying causes …

Multi-task learning is a very challenging problem in reinforcement learning. While training
multiple tasks jointly allow the policies to share parameters across different tasks, the …

As the core technology of hybrid electric vehicles (HEVs), energy management strategy
directly affects the fuel consumption of vehicles. This research proposes a novel …

Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural
Networks (DNNs) for function approximation, has demonstrated considerable success in …

Most deep reinforcement learning (RL) algorithms distill experience into parametric behavior
policies or value functions via gradient updates. While effective, this approach has several …

Our theoretical understanding of deep learning has not kept pace with its empirical success.
While network architecture is known to be critical, we do not yet understand its effect on …

When mastering a complex manipulation task, humans often decompose the task into sub-
skills of their body parts, practice the sub-skills independently, and then execute the sub …

Continual Learning (CL) considers the problem of training an agent sequentially on a set of
tasks while seeking to retain performance on all previous tasks. A key challenge in CL is …

Identifying statistical regularities in solutions to some tasks in multi-task reinforcement
learning can accelerate the learning of new tasks. Skill learning offers one way of identifying …