Scalable Decision Making for Games of Imperfect Information

arXiv:2511.07312 · cs.LG, cs.AI · Submitted 2025-11-10 · Read on arXiv

cs.LG, cs.AI

Submitted: 2025-11-10

Updated: 2026-10-04

Code: https://github.com/braathwaate/strategoevaluator

Project page: https://ataraxosai.github.io

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Mastering Chess with a Transformer Model
• Proximal Policy Optimization Algorithms
• Spatial-Temporal Transformer Networks for Traffic Flow Forecasting
• General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chess
• High entropy leads to symmetry-equivariant policies in Dec-POMDPs
• Layer Normalization
• Learned Belief Search: Efficiently Improving Policies in Partially Observable Settings
• GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks