Active hypothesis testing in unknown environments using recurrent neural networks and model free reinforcement learning

2023/03/19 by George Stamatelis, Stamatelis, George, N. Kalouptsidis +1 · 2 citations
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Distributed Sensor Networks and Detection Algorithms #FOS: Computer and information sciences #Fault Detection and Control Systems #Information Theory (cs.IT) #Machine Learning and Algorithms

paper · pdf · doi:10.48550/arxiv.2303.10623

openalex publication_date 2023/03/19 · openalex created_date 2023/03/22 · openalex updated_date 2026/07/28

Abstract

A combination of deep reinforcement learning and supervised learning is proposed for the problem of active sequential hypothesis testing in completely unknown environments. We make no assumptions about the prior probability, the action and observation sets, and the observation generating process. Our method can be used in any environment even if it has continuous observations or actions, and performs competitively and sometimes better than the Chernoff test, in both finite and infinite horizon problems, despite not having access to the environment dynamics.

Cited by

• Joint Active RIS Configuration and User Power Control for Localization: A Neuroevolution-Based Approach
• Policy Optimization in Multi-Agent Settings under Partially Observable Environments

Related

• Policy Design for Active Sequential Hypothesis Testing using Deep\n Learning
• Fixed-horizon Active Hypothesis Testing
• Reinforcement Learning under Partial Observability Guided by Learned Environment Models
• Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability
• Active inference: demystified and compared