AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Noise as a Natural Regularizer in Markov Decision Processes: Connecting Environmental Stochasticity and Policy Simplicity

Harry Chen, Yiyang Sun, Michal Moshkovitz, Zachery Boner, Lesia Semenova, Cynthia Rudin, Ronald Parr

ICML 2026 · Reinforcement learning › MDPs and planning · approach: Average-reward and regularized MDPs

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 reset noise to the hallway MDP versus lowering the discount factoroptimal policy · Hallway grid MDP, reset noise alpha=0.95policy distance between clean and noisy optimal policiesImproved
add uniform action noise (epsilon 0.3) versus lowering discountoptimal policy · Hallway grid MDPpolicy distanceImproved
add sticky noiseoptimal policy · Hallway grid MDPpolicy equivalenceImproved
add catastrophic-risk transitions (Tightrope MDP) so noise cannot be mimicked by discountingoptimal policy · Tightrope MDPoptimal action choiceHurt
increase random action noise probability with gamma fixed at 0.99PPO policy · 2-Link Reachertrajectory stabilityHurt
lower the discount factorPPO policy · 2-Link Reacherreaching precisionHurt
compare injected noise to reduced discount via reward-distribution JSDPPO policy · 2-Link ReacherJSD of reward distributionsImproved

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