LessWrong · All Posts· XelaP·· 3 小时前AI 评分23
Infra-Bayesian 强化学习智能体学会执行“一箱”博弈
Someone Made an Infra-Bayesian RL Agent, and it One-Boxes!
AI 导读
研究者构建了一个 Infra-Bayesian 强化学习智能体，该智能体成功学会了在“一箱”（One-Box）博弈中做出正确选择。论文已发布在 Arxiv，相关代码已开源至 GitHub 仓库。
来源：LessWrong · All Posts · lesswrong.com