基于迁移学习的视频游戏状态异构预测多任务学习
Multi-Task Learning for Heterogeneous Prediction from Video Game State with Transfer Learning
浏览论文内容
中文总结 AI 辅助
研究视频游戏状态异构预测，通过适配多模态架构，采用跨任务联合训练共享模型，结合多种信息，经实验比较单多任务训练、评估策略及测试预训练等，还研究游戏内迁移，以降低成本并提升泛化能力。
中文摘要 AI 辅助
多任务学习（MTL）是一种用于从视频游戏状态数据进行预测任务的有前景的方法，因为现代游戏遥测提供了来自相同结构化观测的多个相关监督信号。我们研究在基于团队的多人游戏中跨任务联合训练的共享模型，与专门的单任务模型相比，是否能在降低训练和推理成本的同时提高泛化能力。我们将一种用于端点预测的多模态架构适配到一个通用多任务设置，通过图像编码器和基于注意力的交互建模来结合光栅化视觉输入、全局匹配上下文和单位状态信息。在一个大型专有《坦克世界》数据集上的实验比较了单任务和多任务训练，评估了混合损失和冲突梯度的加权策略，并在有限目标数据情况下测试了预训练/微调。我们还研究了在结构化环境变化下游戏地图间的游戏内迁移。
英文摘要
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.
