To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …

Sequential decision making, commonly formalized as Markov Decision Process (MDP)
optimization, is an important challenge in artificial intelligence. Two key approaches to this …

Offline learning is a key part of making reinforcement learning (RL) useable in real systems.
Offline RL looks at scenarios where there is data from a system's operation, but no direct …

Abstract Continual learning (CL)---the ability to continuously learn, building on previously
acquired knowledge---is a natural requirement for long-lived autonomous reinforcement …

Most reinforcement learning methods are based upon the key assumption that the transition
dynamics and reward functions are fixed, that is, the underlying Markov decision process is …

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 …

The objective of lifelong reinforcement learning (RL) is to optimize agents which can
continuously adapt and interact in changing environments. However, current RL approaches …

Planners using accurate models can be effective for accomplishing manipulation tasks in the
real world, but are typically highly specialized and require significant fine-tuning to be …

We propose a framework, called neural-progressive hedging (NP), that leverages stochastic
programming during the online phase of executing a reinforcement learning (RL) policy. The …

We propose a reinforcement learning framework for discrete environments in which an
agent makes both strategic and tactical decisions. The former manifests itself through the …