用多任务学习提升游戏状态预测的通用性与效率
Multi-Task Learning for Heterogeneous Prediction from Video Game State with Transfer Learning
- 共享模型联合训练多个预测任务，融合视觉与状态信息
- 相比单任务模型，多任务训练提升泛化能力并降低开销
- 适合游戏数据分析、迁移学习研究者参考
多任务学习（MTL）在视频游戏状态数据的预测任务中具有潜力，因现代游戏遥测系统能从同一结构化观测中提供多个相关监督信号。我们研究在团队制多人游戏中，共享模型联合训练多个任务是否能提升泛化性能，同时降低训练与推理成本。针对端点预测任务，我们采用一种多模态架构，通过图像编码器和基于注意力的交互建模，融合栅格化视觉输入、全局比赛上下文及单位状态信息。在大规模私有数据集World of Tanks上进行实验，对比单任务与多任务训练效果，评估混合损失权重策略与冲突梯度处理方法，并测试在目标数据有限情况下的预训练/微调策略。还考察了跨地图的游戏中迁移学习在结构化环境变化下的表现。
原文摘要 · Abstract (English)
Multi-task learning (MTL) is a promising approach for prediction tasks derived from video game state data, as modern game telemetry provides multiple related supervision signals from the same structured observations. We study whether a shared model trained jointly across tasks in team-based multiplayer games can improve generalization while reducing training and inference cost compared to specialized single-task models. We adapt a multimodal architecture for endpoint prediction to a general multi-task setting that combines rasterized vision inputs, global match context, and per-unit state information through an image encoder and attention-based interaction modeling. Experiments on a large proprietary World of Tanks dataset compare single-task and multi-task training, evaluate weighting strategies for mixed losses and conflicting gradients, and test pre-training/fine-tuning under limited target-data regimes. We also examine within-game transfer across game maps under structured environment shift.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。