AI Paper Atlas

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

Deep Reinforcement Learning Finds Bayes-Nash Equilibrium in Competitive Newsvendor Problems

Kassian Köck, Fabian Raoul Pieroth, Martin Bichler

ICML 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning

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
train independent PPO agents via self-playcompetitive newsvendor game · symmetric complete informationconvergence to Nash equilibrium: approaches y_i 0.5858 within about 20 iterationsImproved
train independent PPO agents in asymmetric costscompetitive newsvendor game · asymmetric complete informationrelative error to best response: relative errors below 0.4%Improved
train independent PPO agents with private cost typescompetitive newsvendor game · Bayesian game (uniform and Gaussian demand)relative error to best response: relative errors below 1%Improved
change demand from uniform to Gaussian N(0.5, 0.15) (ablation)PPO self-play · Bayesian newsvendorconvergenceNo clear effect
raise penalty p or salvage q to 0.2 (ablation)competitive newsvendor game · complete informationequilibrium stocking: joint stocking exceeds expected total demand of 1.0Improved
use REINFORCE or TD3 instead of PPO (ablation)self-play DRL · competitive newsvendor gameconvergenceNo 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