With recent advances in mobile robotics, autonomous systems, and artificial intelligence,
there is a growing expectation that robots are able to solve complex problems. Many of …

Reinforcement learning (RL) methods usually treat reward functions as black boxes. As
such, these methods must extensively interact with the environment in order to discover …

Abstract In Reinforcement Learning (RL), an agent is guided by the rewards it receives from
the reward function. Unfortunately, it may take many interactions with the environment to …

Reward is the driving force for reinforcement-learning agents. This paper is dedicated to
understanding the expressivity of reward as a way to capture tasks that we would want an …

In this paper we propose Reward Machines {—} a type of finite state machine that supports
the specification of reward functions while exposing reward function structure to the learner …

Although deep reinforcement learning has become a promising machine learning approach
for sequential decision-making problems, it is still not mature enough for high-stake domains …

We present a reinforcement learning (RL) frame-work to synthesize a control policy from a
given linear temporal logic (LTL) specification in an unknown stochastic environment that …

Reinforcement learning (RL) agents seek to maximize the cumulative reward obtained when
interacting with their environment. Users define tasks or goals for RL agents by designing …

The unification of statistical (data-driven) and symbolic (knowledge-driven) methods is
widely recognized as one of the key challenges of modern AI. Recent years have seen a …

We address the problem of teaching a deep reinforcement learning (RL) agent to follow
instructions in multi-task environments. Instructions are expressed in a well-known formal …