Achieving human-like planning and control with multimodal observations in an open world is
a key milestone for more functional generalist agents. Existing approaches can handle …

In a standard view of the reinforcement learning problem, an agent's goal is to efficiently
identify a policy that maximizes long-term reward. However, this perspective is based on a …

In mobile edge computing systems, an edge node may have a high load when a large
number of mobile devices offload their tasks to it. Those offloaded tasks may experience …

In many real-world applications, reinforcement learning (RL) agents might have to solve
multiple tasks, each one typically modeled via a reward function. If reward functions are …

Lifelong learning represents an emerging machine learning paradigm that aims at designing
new methods providing accurate analyses in complex and dynamic real-world …

We consider model-free reinforcement learning (RL) in non-stationary Markov decision
processes. Both the reward functions and the state transition functions are allowed to vary …

Temporal difference (TD) learning is often used to update the estimate of the value function
which is used by RL agents to extract useful policies. In this paper, we focus on value …

This work tackles the problem of robust zero-shot planning in non-stationary stochastic
environments. We study Markov Decision Processes (MDPs) evolving over time and …

A key challenge in lifelong reinforcement learning (RL) is the loss of plasticity, where
previous learning progress hinders an agent's adaptation to new tasks. While regularization …

Consider the lifelong machine learning paradigm whose objective is to learn a sequence of
tasks depending on previous experiences, eg, knowledge library or deep network weights …