mlsanityData to 14 Oct 2026

Pareto-guided Pipeline for Distilling Featherweight AI Agents in Mobile MOBA Games

arXiv 2602.07521 ↗First posted 7 Feb 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent advances in game AI have demonstrated the feasibility of training agents that surpass top-tier human professionals in complex environments such as Honor of Kings (HoK), a leading mobile multiplayer online battle arena (MOBA) game. However, deploying such powerful agents on mobile devices remains a major challenge. On one hand, the intricate multi-modal state representation and hierarchical action space of HoK demand large, sophisticated policy networks that are inherently difficult to compress into lightweight forms. On the other hand, production deployment requires high-frequency inference under strict energy and latency constraints on mobile platform. To the best of our knowledge, bridging large-scale game AI and practical on-device deployment has not been systematically studied. In this work, we propose a Pareto optimality guided pipeline and design a high-efficiency student architecture search space tailored for mobile execution, enabling systematic exploration of the trade-off between performance and efficiency. Experimental results demonstrate that the distilled model achieves remarkable efficiency, including an 12.4× faster inference speed (under 0.5ms per frame) and a 15.6× improvement in energy efficiency (under 0.5mAh per game), while retaining a 40.32% win rate against the original teacher model.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 43 references that are in the map. First posted on arXiv 7 Feb 2026.

Builds on

21 of 43 references.

References · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  5. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  6. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  7. 2014FitNets: Hints for Thin Deep Netscited by 1,653
  8. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  9. 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,121
  10. 2018Rethinking the Value of Network Pruningcited by 599
  11. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 443
  12. 2015Policy Distillationcited by 440
9 more
  1. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 426
  2. 2019TuckER: Tensor Factorization for Knowledge Graph Completioncited by 290
  3. 2015Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applicationscited by 162
  4. 2019Mastering Complex Control in MOBA Games with Deep Reinforcement Learningcited by 161
  5. 2019Distilling Policy Distillationcited by 84
  6. 2020Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kingscited by 18
  7. 2024A Comprehensive Review of Knowledge Distillation in Computer Visioncited by 10
  8. 2019Real-time Policy Distillation in Deep Reinforcement Learningcited by 4
  9. 2024Online Policy Distillation with Decision-Attentioncited by 2

Built on by

Not cited yet.