Decision-making is challenging in robotics environments with continuous object-centric
states, continuous actions, long horizons, and sparse feedback. Hierarchical approaches …

In robotic domains, learning and planning are complicated by continuous state spaces,
continuous action spaces, and long task horizons. In this work, we address these challenges …

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

Creating reinforcement learning (RL) agents that are capable of accepting and leveraging
task-specific knowledge from humans has been long identified as a possible strategy for …

Hierarchical reinforcement learning (HRL) has been proven to be effective for tasks with
sparse rewards, for it can improve the agent's exploration efficiency by discovering high …

Reinforcement learning in problems with symbolic state spaces is challenging due to the
need for reasoning over long horizons. This paper presents a new approach that utilizes …

We propose RAPid-Learn (Learning to Recover and Plan Again), a hybrid planning and
learning method, to tackle the problem of adapting to sudden and unexpected changes in an …

This paper addresses the problem of inventing and using hierarchical representations for
stochastic robot-planning problems. Rather than using hand-coded state or action …

Problems which require both long-horizon planning and continuous control capabilities
pose significant challenges to existing reinforcement learning agents. In this paper we …

Abstract “Open world” environments are those in which novel objects, agents, events, and
more can appear and contradict previous understandings of the environment. This runs …