AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Budgeted Reinforcement Learning in Continuous State Space

Nicolas Carrara, Edouard Leurent, Romain Laroche, Tanguy Urvoy, Odalric-Ambrym Maillard, Olivier Pietquin

NeurIPS 2019 · Reinforcement learning › MDPs and planning · approach: POMDP policy optimization · 9 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
Use risk-sensitive exploration that samples initial budgets uniformly and keeps sampled trajectories within feasible budgets, rather than risk-neutral ε-greedy explorationBFTQ on Corridors · Corridorsreward-cost trade-off performance across budgetsImproved
Use BFTQ instead of FTQ with Lagrangian relaxationBFTQ · Slot-fillingreward-cost trade-off performanceNo clear effect
Use BFTQ instead of FTQ with Lagrangian relaxationBFTQ · highway-envreward-cost trade-off performanceNo clear effect
Use BFTQ instead of FTQ with Lagrangian relaxationBFTQ · Slot-filling and highway-envexpected cost controlImproved
Use BFTQ instead of FTQ with Lagrangian relaxationBFTQ · Slot-filling and highway-envextra-seed varianceImproved
Use BFTQ at budget β=0BFTQ · highway-envexpected cost: ≃ 0.1Hurt

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