AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Efficient Risk-Averse Reinforcement Learning

Ido Greenberg, Yinlam Chow, Mohammad Ghavamzadeh, Shie Mannor

NeurIPS 2022 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 5 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
add soft-risk scheduling and cross-entropy sampler to GCVaR (CeSoR)GCVaR · Guarded MazeCVaR / long path learnedImproved
add only cross-entropy sampler (CeR, no alpha scheduling) (ablation)GCVaR · Guarded Mazelong path learnedNo clear effect
add only soft-risk scheduling (SoR, no CE sampler) (ablation)GCVaR · Guarded Mazelong path learnedHurt
apply CeSoR instead of GCVaRCVaR-PG · Driving GameCVaR cost: 28Improved
warm-start GCVaR from standard PG (ablation)GCVaR · Guarded Mazelong path learnedHurt
increase batch size N for GCVaR (ablation)GCVaR · Guarded Mazelong path learnedNo clear effect
apply CeSoR instead of GCVaRCVaR-PG · Servers AllocationCVaR returnImproved
vary CE smoothness parameter beta (ablation)CeSoR · all benchmarksCVaRNo clear effect

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