A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong
cs.LG, cs.AI, cs.GT
Submitted: 2026-07-07
Updated: 2026-08-29
Comments: 9 pages, 5 figures, 3 tables. Code and models: https://github.com/Nikelroid/adversarial-coevolution
Code: https://github.com/Nikelroid/adversarial-coevolution
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Dota 2 with Large Scale Deep Reinforcement Learning
- Deep Reinforcement Learning from Self-Play in Imperfect-Information Games
- OpenSpiel: A Framework for Reinforcement Learning in Games
- Suphx: Mastering Mahjong with Deep Reinforcement Learning
- Qwen2.5 Technical Report
- Proximal Policy Optimization Algorithms
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks