Multi-agent active perception with prediction rewards

by   Mikko Lauri, et al.

Multi-agent active perception is a task where a team of agents cooperatively gathers observations to compute a joint estimate of a hidden variable. The task is decentralized and the joint estimate can only be computed after the task ends by fusing observations of all agents. The objective is to maximize the accuracy of the estimate. The accuracy is quantified by a centralized prediction reward determined by a centralized decision-maker who perceives the observations gathered by all agents after the task ends. In this paper, we model multi-agent active perception as a decentralized partially observable Markov decision process (Dec-POMDP) with a convex centralized prediction reward. We prove that by introducing individual prediction actions for each agent, the problem is converted into a standard Dec-POMDP with a decentralized prediction reward. The loss due to decentralization is bounded, and we give a sufficient condition for when it is zero. Our results allow application of any Dec-POMDP solution algorithm to multi-agent active perception problems, and enable planning to reduce uncertainty without explicit computation of joint estimates. We demonstrate the empirical usefulness of our results by applying a standard Dec-POMDP algorithm to multi-agent active perception problems, showing increased scalability in the planning horizon.


page 1

page 2

page 3

page 4


CESMA: Centralized Expert Supervises Multi-Agents

We consider the reinforcement learning problem of training multiple agen...

Learning Cooperation and Online Planning Through Simulation and Graph Convolutional Network

Multi-agent Markov Decision Process (MMDP) has been an effective way of ...

Effective Multi-Robot Spatial Task Allocation using Model Approximations

Real-world multi-agent planning problems cannot be solved using decision...

Decentralized Task Allocation in Multi-Robot Systems via Bipartite Graph Matching Augmented with Fuzzy Clustering

Robotic systems, working together as a team, are becoming valuable playe...

Task-Effective Compression of Observations for the Centralized Control of a Multi-agent System Over Bit-Budgeted Channels

We consider a task-effective quantization problem that arises when multi...

Multi-Agent Programming Contest 2019 FIT BUT Team solution

During our participation in MAPC 2019, we have developed two multi-agent...

Exploiting Submodular Value Functions For Scaling Up Active Perception

In active perception tasks, an agent aims to select sensory actions that...

Please sign up or login with your details

Forgot password? Click here to reset