Quasipolynomial Approximate Planning for Decodable POMDPs
Introduces quasipolynomial-time approximate planning algorithms for ρ-decodable POMDPs, which are weaker than observability assumptions.
Stories per day · 30 days
4 stories, newest first · one card per story
Stories tagged #pomdp
A Decentralized Partially Observable Team Decision Methodology with Delayed Information Sharing
A paper gives decentralized agents a way to learn team policies from delayed shared observations.
Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging
Researchers prove off-policy evaluation under history-dependent logging requires exponentially many episodes, resolving a hardness question for model-based POMDP evaluation.
Learning Intrusion Response Strategies for OT Systems
Researchers model OT intrusion response as a POMDP and train PPO-based automated response strategies effective against MITRE attacks in an emulated OT system.