Related papers: A Novel Point-based Algorithm for Multi-agent Cont…
Decentralized (PO)MDPs provide an expressive framework for sequential decision making in a multiagent system. Given their computational complexity, recent research has focused on tractable yet practical subclasses of Dec-POMDPs. We address…
Optimal decision-making under partial observability requires agents to balance reducing uncertainty (exploration) against pursuing immediate objectives (exploitation). In this paper, we introduce a novel policy optimization framework for…
Autonomous agents that drive on roads shared with human drivers must reason about the nuanced interactions among traffic participants. This poses a highly challenging decision making problem since human behavior is influenced by a multitude…
This paper investigates manipulation of multiple unknown objects in a crowded environment. Because of incomplete knowledge due to unknown objects and occlusions in visual observations, object observations are imperfect and action success is…
This work develops novel strategies for optimal planning with semantic observations using continuous state partially observable markov decision processes (CPOMDPs). Two major innovations are presented in relation to Gaussian mixture (GM)…
Partially observable Markov decision processes (POMDPs) have recently become popular among many AI researchers because they serve as a natural model for planning under uncertainty. Value iteration is a well-known algorithm for finding…
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…
We study a large-scale patrol problem with state-dependent costs and multi-agent coordination.We consider heterogeneous agents, rather general reward functions, and the capabilities of tracking agents' trajectories.Given the complexity and…
The main goal in task planning is to build a sequence of actions that takes an agent from an initial state to a goal state. In robotics, this is particularly difficult because actions usually have several possible results, and sensors are…
Partially observable Markov decision processes (POMDPs) provide an elegant mathematical framework for modeling complex decision and planning problems in stochastic domains in which states of the system are observable only indirectly, via a…
Autonomous agents often operate in scenarios where the state is partially observed. In addition to maximizing their cumulative reward, agents must execute complex tasks with rich temporal and logical structures. These tasks can be expressed…
Partially observable Markov decision processes (POMDPs) form an attractive and principled framework for agent planning under uncertainty. Point-based approximate techniques for POMDPs compute a policy based on a finite set of points…
This paper studies the synthesis of a joint control and active perception policy for a stochastic system modeled as a partially observable Markov decision process (POMDP), subject to temporal logic specifications. The POMDP actions…
We consider the online planning problem for a team of agents to discover and track an unknown and time-varying number of moving objects from onboard sensor measurements with uncertain measurement-object origins. Since the onboard sensors…
We consider the problem of designing policies for partially observable Markov decision processes (POMDPs) with dynamic coherent risk objectives. Synthesizing risk-averse optimal policies for POMDPs requires infinite memory and thus…
This paper considers a multiagent, connected, robotic fleet where the primary functionality of the agents is sensing. A distributed multi-sensor control strategy maximizes the value of the collective sensing capability of the fleet, using…
Autonomous vehicles (AVs) need to interact with other traffic participants who can be either cooperative or aggressive, attentive or inattentive. Such different characteristics can lead to quite different interactive behaviors. Hence, to…
Multi-agent large language model (LLM) systems often rely on a controller to coordinate a pool of heterogeneous models, yet existing controllers are typically limited to one-shot routing: they select a model once and return its output…
A key objective of multi-agent surveillance systems is to monitor a much larger region than the limited field-of-view (FoV) of any individual agent by successfully exploiting cooperation among multi-view agents. Whenever either a…
Large language model (LLM)-based agents are increasingly used to perform complex, multi-step workflows in regulated settings such as compliance and due diligence. However, many agentic architectures rely primarily on prompt engineering of a…