AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Online Robust Reinforcement Learning with Model Uncertainty

Yue Wang, Shaofeng Zou

NeurIPS 2021 · Reinforcement learning › MDPs and planning · approach: Function approximation in RL theory · 6 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
robust Q-learning instead of vanilla Q-learning, trained on perturbed MDPQ-learning · FrozenLake-v0 and CartPole-v0accumulated discounted rewardImproved
larger perturbation p and radius Rrobust Q-learning vs vanilla · FrozenLake-v0 and CartPole-v0accumulated discounted rewardImproved
robust TDC instead of vanilla TDC with linear function approximationTDC · FrozenLake-v0 4x4squared gradient normImproved
robust TDC has smaller variance across 30 runsTDC · FrozenLake-v0 4x4variance of gradient normImproved
robust Q-learning instead of RARL adversarial trainingQ-learning · Taxi-v3accumulated discounted rewardImproved
robust Q-learning instead of RARLQ-learning · Taxi-v3training varianceImproved

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