Related papers: Safe Explicable Policy Search
Reinforcement learning techniques successfully generate convincing agent behaviors, but it is still difficult to tailor the behavior to align with a user's specific preferences. What is missing is a communication method for the system to…
Over the last few years, the concept of Artificial Intelligence has become central in different tasks concerning both our daily life and several working scenarios. Among these tasks automated planning has always been central in the AI…
A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world,…
Autonomous agents (robots) face tremendous challenges while interacting with heterogeneous human agents in close proximity. One of these challenges is that the autonomous agent does not have an accurate model tailored to the specific human…
This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL), such that the safety constraint violations are bounded at any point during learning. In a variety of RL applications the safety of the…
Recent superhuman results in games have largely been achieved in a variety of zero-sum settings, such as Go and Poker, in which agents need to compete against others. However, just like humans, real-world AI systems have to coordinate and…
People routinely infer the goals of others by observing their actions over time. Remarkably, we can do so even when those actions lead to failure, enabling us to assist others when we detect that they might not achieve their goals. How…
Despite significant advancements in large language models (LLMs) that enhance robot agents' understanding and execution of natural language (NL) commands, ensuring the agents adhere to user-specified constraints remains challenging,…
The recent enthusiasm for artificial intelligence (AI) is due principally to advances in deep learning. Deep learning methods are remarkably accurate, but also opaque, which limits their potential use in safety-critical applications. To…
The past years have presented a surge in (AI) development, fueled by breakthroughs in deep learning, increased computational power, and substantial investments in the field. Given the generative capabilities of more recent AI systems, the…
Suppose an agent asserts that it will move through an environment in some way. When the agent executes its motion, how does one verify the claim? The problem arises in a range of contexts including in validating safety claims about robot…
Deep search agents, which aim to answer complex questions requiring reasoning across multiple documents, can significantly speed up the information-seeking process. Collecting human annotations for this application is prohibitively…
Reinforcement learning (RL) is ubiquitous in the development of modern AI systems. However, state-of-the-art RL agents require extensive, and potentially unsafe, interactions with their environments to learn effectively. These limitations…
We introduce a novel simulation-based approach to identify hazards that result from unexpected worker behavior in human-robot collaboration. Simulation-based safety testing must take into account the fact that human behavior is variable and…
From software development to robot control, modern agentic systems decompose complex objectives into a sequence of subtasks and choose a set of specialized AI agents to complete them. We formalize agentic workflows as directed acyclic…
Algorithmic recommendations and decisions have become ubiquitous in today's society. Many of these data-driven policies, especially in the realm of public policy, are based on known, deterministic rules to ensure their transparency and…
Physical inactivity remains a critical global health issue, yet scalable strategies for sustained motivation are scarce. Conversational agents designed as simulated exercising peers (SEPs) represent a promising alternative, but their…
Automated persuasion systems (APS) aim to persuade a user to believe something by entering into a dialogue in which arguments and counterarguments are exchanged. To maximize the probability that an APS is successful in persuading a user, it…
Safety is the priority concern when applying reinforcement learning (RL) algorithms to real-world control problems. While policy iteration provides a fundamental algorithm for standard RL, an analogous theoretical algorithm for safe RL…
This paper addresses semantic planning problems in unknown environments under perceptual uncertainty. The environment contains multiple unknown semantically labeled regions or objects, and the robot must reach desired locations while…