Artificial intelligence (AI) and especially reinforcement learning (RL) have the potential to
enable agents to learn and perform tasks autonomously with superhuman performance …

Correct-by-construction synthesis is a cornerstone of the confluence of formal methods and
control theory towards designing safety-critical systems. Instead of following the time-tested …

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 reinforcement learning (RL), a reward function that aligns exactly with a task's true
performance metric is often necessarily sparse. For example, a true task metric might …

Toward verified artificial intelligence Page 1 46 COMMUNICATIONS OF THE ACM | JULY
2022 | VOL. 65 | NO. 7 contributed articles ILL US TRA TION B Y PETER CRO W THER A …

We study reward decomposition for explaining the decisions of reinforcement learning (RL)
agents. The approach decomposes rewards into sums of semantically meaningful reward …

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 study the problem of learning control policies for complex tasks given by logical
specifications. Recent approaches automatically generate a reward function from a given …