AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Solving Risk-Sensitive POMDPs With and Without Cost Observations

Ping Hou, William Yeoh, Pradeep Varakantham

AAAI 2016 · Reinforcement learning › MDPs and planning · approach: POMDP policy optimization · 17 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
observe actual costs and use them in belief updatesDFS (optimal) · Random POMDPs |S|=100, theta0=1.50*Cdetreachable probability: 0.205 -> 0.214Improved
observe actual costsDFS · Taxi domainreachable probability: 0.317 -> 0.317No clear effect
observe actual costsDFS · Random POMDPs |S|=100average runtime (ms): 3919 -> 8735Hurt
DFS search over reachable beliefs instead of FVIRS-POMDP solving · Random POMDPs |S|=100, costs unobservedreachable probability: 0.169 -> 0.205Improved
add dominated-vector pruning to FVI (ablation)FVI · Random POMDPs |S|=100, costs unobservedsolved instances (%): 6 -> 10Improved
increase PB-FVI belief points from 10 to 1000 (ablation)PB-FVI · Random POMDPs |S|=100, costs unobservedreachable probability: 0.185 -> 0.205Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy