Recent advancements in multi-agent reinforcement learning (MARL) have demonstrated its potential and its applications in modern games. Beginning with foundational work and progressing to landmark achievements such as AlphaStar in StarCraft II and OpenAI Five in Dota 2, MARL has proven capable of achieving superhuman performance across diverse game environments through techniques like self-play, supervised learning, and deep reinforcement learning. With its growing impact, a comprehensive review has become increasingly important in this field. This paper aims to provide a thorough examination of MARL's application from turn-based two-agent games to real-time multi-agent video games including popular genres such as Sports games, First-Person Shooter (FPS) games, Real-Time Strategy (RTS) games and Multiplayer Online Battle Arena (MOBA) games. We analyze critical challenges posed by MARL in video games, including nonstationary, partial observability, sparse rewards, team coordination, and scalability, and highlight successful implementations in games like Roller Champions, Rocket League, Minecraft, Quake III Arena, StarCraft II, Dota 2, Honor of Kings, etc. This paper offers insights into MARL in video game AI and also proposes future research directions to advance MARL and its applications in game technology, inspiring further innovation in this rapidly evolving field.

In this paper, a new method for temperature prediction combining Random Forest (RF) and Long Short-Term Memory Network (LSTM) is proposed to address the challenges in the field of weather prediction. The method combines the advantages of RF and LSTM, which considers the temporal correlation of meteorological data and captures the intrinsic correlation among meteorological elements. While LSTM mines the temporal patterns in the historical weather data, RF provides more informative input data, which improves the timeliness and accuracy of the prediction. Compared with the LSTM model, the RF-LSTM model has improved the RMSE, MAE, and MAPE values by 0.27, 0.22, and 0.07, respectively, and the RF-LSTM model performs significantly in the temperature prediction in Nanjing with high prediction accuracy and stability. The method provides a new idea for meteorological prediction, which not only improves the overall level of prediction, but also provides valuable guidance for people's production and life.