AI Paper Atlas

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

Time-Consistent Robust Multi-Objective Reinforcement Learning via a Bellman–Isaacs Weight-Adversary Recursion

Mingxi Hu, Meiling Yu

ICML 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees

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 time-consistent Bellman-Isaacs weight adversary instead of preference-conditioned baselines (CN-DQN, Envelope, PCN, fixed-weight DQN)proposed method · Timespeed, Timemove, DeepSeaTreasure under BR-K (lambda=1.0)WRRImproved
evaluate with BR-K (min over K independent best-response adversaries) rather than a single adversaryBR-K protocol · evaluationrobustness estimateImproved
increase switching cost lambda (ablation)proposed method · MO-Gymnasium benchmarksDRIFTImproved

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