mlsanityData to 7 Oct 2026

Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment

arXiv 2406.01103 ↗First posted 3 Jun 2024cs.AI cs.HC cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Deep Reinforcement Learning (DRL) agents have demonstrated impressive success in a wide range of game genres. However, existing research primarily focuses on optimizing DRL competence rather than addressing the challenge of prolonged player interaction. In this paper, we propose a practical DRL agent system for fighting games named Sh=ukai, which has been successfully deployed to Naruto Mobile, a popular fighting game with over 100 million registered users. Sh=ukai quantifies the state to enhance generalizability, introducing Heterogeneous League Training (HELT) to achieve balanced competence, generalizability, and training efficiency. Furthermore, Sh=ukai implements specific rewards to align the agent's behavior with human expectations. Sh=ukai's ability to generalize is demonstrated by its consistent competence across all characters, even though it was trained on only 13% of them. Additionally, HELT exhibits a remarkable 22% improvement in sample efficiency. Sh=ukai serves as a valuable training partner for players in Naruto Mobile, enabling them to enhance their abilities and skills.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 34 of its 59 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

34 of 59 references.

References · 34

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  6. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  7. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  8. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  9. 2017Hindsight Experience Replaycited by 1,096
  10. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  11. 2018Quantifying Generalization in Reinforcement Learningcited by 345
  12. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 265
22 more
  1. 2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 260
  2. 2017DeepStack: Expert-Level Artificial Intelligence in No-Limit Pokercited by 228
  3. 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 153
  4. 2020Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehiclescited by 101
  5. 2018Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learningcited by 91
  6. 2020Towards Playing Full MOBA Games with Deep Reinforcement Learningcited by 78
  7. 2016Learning to Act by Predicting the Futurecited by 36
  8. 2024Cross-Domain Policy Adaptation by Capturing Representation Mismatchcited by 24
  9. 2019Creating Pro-Level AI for a Real-Time Fighting Game Using Deep Reinforcement Learningcited by 14
  10. 2023Normalization Enhances Generalization in Visual Reinforcement Learningcited by 13
  11. 2022DareFightingICE Competition: A Fighting Game Sound Design and AI Competitioncited by 10
  12. 2023Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learningcited by 9
  13. 2022Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learningcited by 8
  14. 2023Conceptual Reinforcement Learning for Language-Conditioned Taskscited by 8
  15. 2023Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learningcited by 8
  16. 2022DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learningcited by 7
  17. 2024Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equationcited by 7
  18. 2022Object-Category Aware Reinforcement Learningcited by 6
  19. 2024Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidencecited by 5
  20. 2023Online Prototype Alignment for Few-shot Policy Transfercited by 4
  21. 2022Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AIcited by 3
  22. 2024Balancing the AI Strength of Roles in Self-Play Training with Regret Matching+cited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 1.

7 papers.

  1. 2025AVA: Attentive VLM Agent for Mastering StarCraft IIcited by 5
  2. 2025Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectivescited by 4
  3. 2025EvoCurr: Self-evolving Curriculum with Behavior Code Generation for Complex Decision-makingcited by 3
  4. 2025Human-Like Goalkeeping in a Realistic Football Simulation: a Sample-Efficient Reinforcement Learning Approachcited by 2
  5. 2025Improving Sample Efficiency in Multi-Agent Reinforcement Learning for Simulated Football Games via Explorationcited by 1
  6. 2025Enhancing Player Enjoyment with a Two-Tier DRL and LLM-Based Agent System for Fighting Gamescited by 0
  7. 2026RSI-Router: Evolving Subtask-Level LLM Routing and Skills for Cost-Efficient Agentscited by 0