按年被提到
20212021 · 3 次2026
强化学习与智能体›进化策略与探索·arXiv:2101.03958 · cs.LG

Evolving Reinforcement Learning Algorithms

John D. Co-Reyes, Yingjie Miao, Daiyi Peng, Esteban Real, Sergey Levine, Quoc V. Le, Honglak Lee, Aleksandra Faust · 2021
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2021-01-17 · 最近 2021-02-17
3不同的人
2活跃月份
3讨论串
51被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We propose a method for meta-learning reinforcement learning algorithms by searching over the space of computational graphs which compute the loss function for a value-based model-free RL agent to optimize. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. Our method can both learn from scratch and bootstrap off known existing algorithms, like DQN, enabling interpretable modifications which improve performance. Learning from scratch on simple classical control and gridworld tasks, our method rediscovers the temporal-difference (TD) algorithm. Bootstrapped from DQN, we highlight two learned algorithms which obtain good generalization performance over other classical control tasks, gridworld type tasks, and Atari games. The analysis of the learned algorithm behavior shows resemblance to recently proposed RL algorithms that address overestimation in value-based methods.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)

讨论串里没有 ≥100 字的评论,只有提交记录。

被提交为 story · 3 次