按年被提到
20112012 · 1 次2026
强化学习与智能体›博弈与游戏 AI·arXiv:1112.5309 · cs.AI

POWERPLAY: Training an Increasingly General Problem Solver by Continually Searching for the Simplest Still Unsolvable Problem

Jürgen Schmidhuber · 2011
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2012-11-21 · 最近 2019-12-06
2不同的人
2活跃月份
2讨论串
121被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Most of computer science focuses on automatically solving given computational problems. I focus on automatically inventing or discovering problems in a way inspired by the playful behavior of animals and humans, to train a more and more general problem solver from scratch in an unsupervised fashion. Consider the infinite set of all computable descriptions of tasks with possibly computable solutions. The novel algorithmic framework POWERPLAY (2011) continually searches the space of possible pairs of new tasks and modifications of the current problem solver, until it finds a more powerful problem solver that provably solves all previously learned tasks plus the new one, while the unmodified predecessor does not. Wow-effects are achieved by continually making previously learned skills more efficient such that they require less time and space. New skills may (partially) re-use previously learned skills. POWERPLAY's search orders candidate pairs of tasks and solver modifications by their conditional computational (time & space) complexity, given the stored experience so far. The new task and its corresponding task-solving skill are those first found and validated. The computational costs of validating new tasks need not grow with task repertoire size. POWERPLAY's ongoing search for novelty keeps breaking the generalization abilities of its present solver. This is related to Goedel's sequence of increasingly powerful formal theories based on adding formerly unprovable statements to the axioms without affecting previously provable theorems. The continually increasing repertoire of problem solving procedures can be exploited by a parallel search for solutions to additional externally posed tasks. POWERPLAY may be viewed as a greedy but practical implementation of basic principles of creativity. A first experimental analysis can be found in separate papers [53,54].

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someguyorother · 2019-12

“There does seem to be a kind of turnpike theory-like effect to technological development. I'm reminded of Schmidhuber's PowerPlay (https://arxiv.org/abs/1112.5309), too. It just trains on increasingly difficult problems with no direct objective function beyond solving the current problem and devising a harder one.”

How “randomizers” are breathing new life into old games原评论 ↗
被提交为 story · 1 次