相关论文: TAB-Fields: A Maximum Entropy Framework for Missio…

In many engineering systems, proper predictive maintenance and operational control are essential to increase efficiency and reliability while reducing maintenance costs. However, one of the major challenges is that many sensors are used for…

Qualitative opacity of a secret is a security property, which means that a system trajectory satisfying the secret is observation-equivalent to a trajectory violating the secret. In this paper, we study how to synthesize a control policy…

Simulation provides a safe and efficient way to generate useful data for learning complex robotic tasks. However, matching simulation and real-world dynamics can be quite challenging, especially for systems that have a large number of…

Purposeful behavior in robotic assistants requires the integration of multiple components and technological advances. Often, the problem is reduced to recognizing explicit prompts, which limits autonomy, or is oversimplified through…

Transfer reinforcement learning aims to improve the sample efficiency of solving unseen new tasks by leveraging experiences obtained from previous tasks. We consider the setting where all tasks (MDPs) share the same environment dynamic…

Currently, in the study of multiagent systems, the intentions of agents are usually ignored. Nonetheless, as pointed out by Theory of Mind (ToM), people regularly reason about other's mental states, including beliefs, goals, and intentions,…

Reinforcement learning in partially observed Markov decision processes (POMDPs) faces two challenges. (i) It often takes the full history to predict the future, which induces a sample complexity that scales exponentially with the horizon.…

To achieve autonomy in complex real-world exploration missions, we consider deployment strategies for a team of robots with heterogeneous autonomy capabilities. In this work, we formulate a multi-robot exploration mission and compute an…

Open intent detection is a significant problem in natural language understanding, which aims to identify the unseen open intent while ensuring known intent identification performance. However, current methods face two major challenges.…

Interactive partially observable Markov decision processes (I-POMDP) provide a formal framework for planning for a self-interested agent in multiagent settings. An agent operating in a multiagent environment must deliberate about the…

Intention deception involves computing a strategy which deceives the opponent into a wrong belief about the agent's intention or objective. This paper studies a class of probabilistic planning problems with intention deception and…

A Markov Decision Process (MDP) is a popular model for reinforcement learning. However, its commonly used assumption of stationary dynamics and rewards is too stringent and fails to hold in adversarial, nonstationary, or multi-agent…

In this paper, we address the problem of stochastic motion planning under partial observability, more specifically, how to navigate a mobile robot equipped with continuous range sensors such as LIDAR. In contrast to many existing robotic…

Artificial intelligence has undergone immense growth and maturation in recent years, though autonomous systems have traditionally struggled when fielded in diverse and previously unknown environments. DARPA is seeking to change that with…

Deploying multi-robot systems in environments shared with dynamic and uncontrollable agents presents significant challenges, especially for large robot fleets. In such environments, individual robot operations can be delayed due to…

Attention control is a key cognitive ability for humans to select information relevant to the current task. This paper develops a computational model of attention and an algorithm for attention-based probabilistic planning in Markov…

Intention recognition, or the ability to anticipate the actions of another agent, plays a vital role in the design and development of automated assistants that can support humans in their daily tasks. In particular, industrial settings pose…

Offline meta-reinforcement learning aims to equip agents with the ability to rapidly adapt to new tasks by training on data from a set of different tasks. Context-based approaches utilize a history of state-action-reward transitions --…

The state-of-the-art multi-agent reinforcement learning (MARL) methods have provided promising solutions to a variety of complex problems. Yet, these methods all assume that agents perform synchronized primitive-action executions so that…

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…