AI Paper Atlas

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

Recurrent Structural Policy Gradient for Partially Observable Mean Field Games

Clarisse Wibault, Johannes Forkel, Sebastian Rene Towers, Tiphaine Wibault, Juan Agustin Duque, George Whittle, Andreas Schaab, Yucheng Yang, Chiyuan Wang, Michael A Osborne, Benjamin Moll, Jakob Nicolaus Foerster

ICML 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Trajectory reuse in policy gradients · 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 history-aware recurrent policy (RSPG) instead of memoryless SPG (ablation)Hybrid structural policy gradient · Beach Bar and Linear Quadratic (partially observable)exploitabilityImproved
use history-aware recurrent policy (RSPG) instead of memoryless SPG (ablation)Hybrid structural policy gradient · MacroeconomicsexploitabilityNo clear effect
use history-aware recurrent policy (RSPG) instead of memoryless SPG (ablation)Hybrid structural policy gradient · Macroeconomicsanticipatory behaviourImproved
add recurrence over public observation history (GRU) to SPG (ablation)SPG · convergence speed vs wall-clockconvergence rateNo clear effect
use known transition dynamics (HSM) instead of sample-based RLmean-field policy learning · Linear Quadratic, Beach Bar, Macroeconomicswall-clock convergence: approximately an order-of-magnitude fasterImproved
add recurrence to IPPO (RIPPO)IPPO · training wall-clock timetraining speedHurt
use M-OMD (Q-function based) in large state-action spaceM-OMD · MacroeconomicsexploitabilityHurt
parameterise underlying continuous distribution with softmax over density on action grid instead of categorical logits (ablation)RSPG policy · MacroeconomicsexploitabilityImproved
compute mean-field updates in functional form rather than matrix multiplicationMFAX · Linear Quadratic mean-field updateupdate time: over 10x and 1000x faster than OpenSpiel and MFGLibImproved

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