AI Paper Atlas

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

Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity

Aneri Muni, Vincent Taboga, Esther Derman, Pierre-Luc Bacon, Erick Delage

ICML 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Tree search and policy optimization · 0 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 the transformed CVaR Bellman operator with dense per-step reward instead of the sparse-reward augmented operator, on bounded functionsstatic CVaR value iteration · theory (bounded value functions)fixed point / contractionImproved
Increase discretization resolution of the augmented state (100 to 5000 bins) (ablation)static CVaR value iteration with lower/upper bounding operators · stochastic gridworldgap between upper and lower bound CVaR performanceImproved
Lower risk level alpha (toward robust) with the learned CVaR policiesstatic CVaR Q-VI and Q-learning · stochastic gridworldlower tail of return distribution / crater entriesImproved
Use risk-averse CVaR policy instead of risk-neutral policy at small alphastatic CVaR agents · stochastic gridworldempirical CVaRImproved
Use model-free Q-learning instead of Q-VIstatic CVaR algorithms · stochastic gridworld, alpha in [0.5, 0.6]policy behavior and varianceMixed
Run static CVaR Q-learning with block updates over all budgets for 50k iterationsstatic CVaR Q-learning · stochastic gridworlddistance to Q-VI value functionImproved

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