English(EN)Player-1: Learning to Play from Synthetic Experience
AI代理通过合成经验和新颖的训练方法学习复杂游戏 · 跟踪7个来源
作者PulseAugur 编辑部·[8 个来源]·
研究人员正在探索先进的技术，使AI代理能够学习复杂的游戏，超越简单的演示。一种方法GameSmith使用大型语言模型来合成新游戏进行训练，提高了在基准测试上的表现。另一种方法VQEL采用向量量化来处理新兴语言游戏中的离散通信协议，增强了训练稳定性。此外，Player-1利用合成经验来训练游戏控制代理，在各种环境中表现优于基线方法。这些研究突显了AI通过新颖的训练范式掌握复杂任务的能力日益增强。
AI
arXiv:2610.19868v1 Announce Type: cross Abstract: Training LLM agents on long-horizon interactive tasks with reinforcement learning typically relies on human-annotated tasks and reliable verification, both expensive to construct for stateful environments. Self-play offers an alte…
arXiv:2610.17391v1 Announce Type: new Abstract: Amazing breakthroughs in reinforcement learning have taken place. Computers teach themselves to play Chess and Go and beat world champions. There is talk about expanding application areas towards general artificial intelligence (AI)…
arXiv cs.AI
TIER_1English(EN)·Weixian Waylon Li, Jiaxin Zhang, Han Zhou, Chengzu Li, Ke Wang, Fengxiang He, Yiwen Guo·
arXiv:2610.13995v1 Announce Type: cross Abstract: Post-training large language models (LLMs) on two-player zero-sum games provides a verifiable reward, and the gains have been shown to transfer to general reasoning. Existing pipelines, however, rely on a handful of hand-written g…
arXiv:2411.06403v4 Announce Type: replace Abstract: Why can neural networks struggle to learn optimal play in a game with a simple, efficient solution algorithm? Motivated by empirical difficulties with parity in impartial games, we use NIM to study a representational bottleneck …
arXiv:2503.04940v3 Announce Type: replace-cross Abstract: Emergent Language (EL) focuses on the emergence of communication among artificial agents. Although symbolic communication channels more closely mirror the discrete nature of human language, learning such protocols remains …
Computer-use agents have demonstrated strong capabilities in interpreting screens and executing keyboard and mouse actions. However, games, with their visually rich worlds and diverse mechanics, remain challenging and offer a demanding next step toward general digital control. Cu…
arXiv:2610.20584v1 Announce Type: new Abstract: Computer-use agents have demonstrated strong capabilities in interpreting screens and executing keyboard and mouse actions. However, games, with their visually rich worlds and diverse mechanics, remain challenging and offer a demand…
arXiv:2610.18899v1 Announce Type: cross Abstract: Thompson sampling (TS) achieves logarithmic and asymptotically optimal regret in classical stochastic bandits, but its behavior in multi-agent learning remains less understood. We study TS in an unknown finite two-player zero-sum …
