English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Partially Observable Markov Decision Processes (POMDPs) can model complexsequential decision-making problems under stochastic and uncertainenvironments. A main reason hindering their broad adoption in real-worldapplications is the lack of availability of a suitable POMDP model or asimulator thereof. Available solution algorithms, such as ReinforcementLearning (RL), require the knowledge of the transition dynamics and theobservation generating process, which are often unknown and non-trivial toinfer. In this work, we propose a combined framework for inference and robustsolution of POMDPs via deep RL. First, all transition and observation modelparameters are jointly inferred via Markov Chain Monte Carlo sampling of ahidden Markov model, which is conditioned on actions, in order to recover fullposterior distributions from the available data. The POMDP with uncertainparameters is then solved via deep RL techniques with the parameterdistributions incorporated into the solution via domain randomization, in orderto develop solutions that are robust to model uncertainty. As a furthercontribution, we compare the use of transformers and long short-term memorynetworks, which constitute model-free RL solutions, with amodel-based/model-free hybrid approach. We apply these methods to thereal-world problem of optimal maintenance planning for railway assets.

POMDP inference and robust solution via deep reinforcement learning: An application to railway optimal maintenance