按年被提到
20162016 · 3 次2026
强化学习与智能体›进化策略与探索·arXiv:1611.05397 · cs.LG

Reinforcement Learning with Unsupervised Auxiliary Tasks

Max Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki, Tom Schaul, Joel Z Leibo, David Silver, Koray Kavukcuoglu · 2016
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2016-11-17 · 最近 2016-12-05
3不同的人
2活跃月份
3讨论串
825被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possible training signals. In this paper, we introduce an agent that also maximises many other pseudo-reward functions simultaneously by reinforcement learning. All of these tasks share a common representation that, like unsupervised learning, continues to develop in the absence of extrinsic rewards. We also introduce a novel mechanism for focusing this representation upon extrinsic rewards, so that learning can rapidly adapt to the most relevant aspects of the actual task. Our agent significantly outperforms the previous state-of-the-art on Atari, averaging 880\% expert human performance, and a challenging suite of first-person, three-dimensional \emph{Labyrinth} tasks leading to a mean speedup in learning of 10$\times$ and averaging 87\% expert human performance on Labyrinth.

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

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论sapphireblue · 2016-12

“Looks like the "UNREAL" (https://arxiv.org/abs/1611.05397), "Learning to reinforcement learn" (https://arxiv.org/abs/1611.05763) and "RL^2" (https://arxiv.org/abs/1611.02779) are state of art in pure RL for now. Finally there is a trend of using recurrent neural network as a top component of the Q-network. Perhaps we will see even more sophisticated RNNs…”

OpenAI Universe原评论 ↗
被提交为 story · 2 次