mlsanityData to 14 Oct 2026

RL for games and combinatorial optimization

560 papers1 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: reinforcement, reinforcement learning, games, policy, problem

Key facts. RL for games and combinatorial optimization: 560 papers on arXiv since 2024 (data through 14 Oct 2026). 6 of its 560 mapped papers (1%) cite “Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms” (2024, arXiv 2401.11963). 9 new papers 30 Sep–14 Oct.

What’s new

30 Sep – 14 Oct 2026

9 new papers, 30 Sep – 14 Oct; 1 this week.

  1. This week · 1
  2. Learning to Play: Reinforcement Learning and Games
  3. Earlier · 8
  4. Integrating AIRL-Based Reward Estimation into a Control Method Using Fuzzy Inference and Policy Gradient also fits: Deep RL algorithms and representations
  5. Toward Maximizing Algebraic Connectivity via Density-Dependent Backbone Construction and Reinforcement Learning Completion also fits: RL for energy, networks and operations
  6. Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition
  7. Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games also fits: Deep RL algorithms and representations
  8. Self-Referenced Social Preferences: Cooperation without Observing Others Rewards also fits: RL training of language and agent models
  9. Factoriax: A GPU-Accelerated Factorio-Style Simulator for Reinforcement Learning also fits: RL for energy, networks and operations
  10. Mastering Atari 2600 Games with Discovered Options also fits: Deep RL algorithms and representations
  11. Reinforcement Learning to Accelerate Primal-Dual Hybrid Gradient for Linear Programming also fits: RL theory and sample complexity

Foundations

Most cited by papers here

  1. Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms2024cited by 6 here
  2. When is Mean-Field Reinforcement Learning Tractable and Relevant?2024cited by 6 here
  3. Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolution2024cited by 6 here
  4. Pareto Set Learning for Multi-Objective Reinforcement Learning2025cited by 6 here
  5. Reevaluating Policy Gradient Methods for Imperfect-Information Games2025cited by 6 here

Lineage

The papers this direction builds on, oldest first.

  1. 2024Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithmscited by 6 here
  2. 2024Meta-Learning Linear Quadratic Regulators: A Policy Gradient MAML Approach for Model-free LQRcited by 3 here
  3. 2024On the Limitations of Markovian Rewards to Express Multi-Objective, Risk-Sensitive, and Modal Taskscited by 3 here
  4. 2024INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformercited by 5 here
  5. 2024Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RLcited by 4 here
  6. 2024When is Mean-Field Reinforcement Learning Tractable and Relevant?cited by 6 here
  7. 2024Truly No-Regret Learning in Constrained MDPscited by 3 here
  8. 2024Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolutioncited by 6 here
  9. 2024Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspectivecited by 5 here
  10. 2024Auto-configuring Exploration-Exploitation Tradeoff in Evolutionary Computation via Deep Reinforcement Learningcited by 5 here
  11. 2024Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lenscited by 5 here
  12. 2024Reinforcement learningcited by 7 here
12 more
  1. 2024The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithmcited by 4 here
  2. 2024Unified continuous-time q-learning for mean-field game and mean-field control problemscited by 4 here
  3. 2024Gymnasium: A Standard Interface for Reinforcement Learning Environmentscited by 12 here
  4. 2024Full error analysis of policy gradient learning algorithms for exploratory linear quadratic mean-field control problem in continuous time with common noisecited by 5 here
  5. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 4 here
  6. 2024Mean Field LQG Social Optimization: A Reinforcement Learning Approachcited by 5 here
  7. 2025Pareto Set Learning for Multi-Objective Reinforcement Learningcited by 6 here
  8. 2025Reevaluating Policy Gradient Methods for Imperfect-Information Gamescited by 6 here
  9. 2025Accuracy of Discretely Sampled Stochastic Policies in Continuous-time Reinforcement Learningcited by 4 here
  10. 2025Policy Gradient for LQR with Domain Randomizationcited by 5 here
  11. 2025Policy Gradient Adaptive Control for the LQR: Indirect and Direct Approachescited by 4 here
  12. 2025Scalable Decision Making for Games of Imperfect Informationcited by 5 here

The 24 most cited of 282.

Browse

30 of 560, ranked 6–35

  1. 6Policy Gradient for LQR with Domain Randomization20255
  2. 7Scalable Decision Making for Games of Imperfect Information20255
  3. 8INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer20245
  4. 9Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective20245
  5. 10Auto-configuring Exploration-Exploitation Tradeoff in Evolutionary Computation via Deep Reinforcement Learning20245
  6. 11Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens20245
  7. 12Full error analysis of policy gradient learning algorithms for exploratory linear quadratic mean-field control problem in continuous time with common noise20245
  8. 13Mean Field LQG Social Optimization: A Reinforcement Learning Approach20245
  9. 14Policy Gradient Adaptive Control for the LQR: Indirect and Direct Approaches20254
  10. 15Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL20244
All 30
  1. 16The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm20244
  2. 17Unified continuous-time q-learning for mean-field game and mean-field control problems20244
  3. 18Model-free policy gradient for discrete-time mean-field control20263
  4. 19Reinforcement Learning-based Self-adaptive Differential Evolution through Automated Landscape Feature Learning20253
  5. 20Meta-Learning Linear Quadratic Regulators: A Policy Gradient MAML Approach for Model-free LQR20243
  6. 21Population-aware Online Mirror Descent for Mean-Field Games by Deep Reinforcement Learning20243
  7. 22Self-Improvement for Neural Combinatorial Optimization: Sample without Replacement, but Improvement20243
  8. 23MF-OML: Online Mean-Field Reinforcement Learning with Occupation Measures for Large Population Games20243
  9. 24Fairness in Reinforcement Learning: A Survey20243
  10. 25Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning20243
  11. 26Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance20243
  12. 27Continuous-time q-learning for mean-field control with common noise, part-I: Theoretical foundations20262
  13. 28Continuous-time q-learning for mean-field control with common noise, part-II: q-learning algorithms20262
  14. 29Policy Gradient for Continuous-Time Mean-Field Control20262
  15. 30Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces20252
  16. 31Convergence Guarantees of Model-free Policy Gradient Methods for LQR with Stochastic Data20252
  17. 32Robust Mean Field Social Control: A Unified Reinforcement Learning Framework20252
  18. 33On Generalization Across Environments In Multi-Objective Reinforcement Learning20252
  19. 34Surrogate Learning in Meta-Black-Box Optimization: A Preliminary Study20252
  20. 35Preference Optimization for Combinatorial Optimization Problems20252