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) offer an elegantframework to model sequential decision making in uncertain environments.Solving POMDPs online is an active area of research and given the size ofreal-world problems approximate solvers are used. Recently, a few approacheshave been suggested for solving POMDPs by using MDP solvers in conjunction withimitation learning. MDP based POMDP solvers work well for some cases, whilecatastrophically failing for others. The main failure point of such solvers isthe lack of motivation for MDP solvers to gain information, since under theirassumption the environment is either already known as much as it can be or theuncertainty will disappear after the next step. However for solving POMDPproblems gaining information can lead to efficient solutions. In this paper wederive a set of conditions where MDP based POMDP solvers are provablysub-optimal. We then use the well-known tiger problem to demonstrate suchsub-optimality. We show that multi-resolution, budgeted information gatheringcannot be addressed using MDP based POMDP solvers. The contribution of thepaper helps identify the properties of a POMDP problem for which the use of MDPbased POMDP solvers is inappropriate, enabling better design choices.

Hindsight is Only 50/50: Unsuitability of MDP based Approximate POMDP Solvers for Multi-resolution Information Gathering