paper-with-me

홈 › Papers

A Comparison of Decision Algorithms on Newcomblike Problems

2023-05-31 · Alex Altair

When formulated using Bayesian networks, two standard decision algorithms (Evidential Decision Theory and Causal Decision Theory) can be shown to fail systematically when faced with aspects of the prisoner's dilemma and so-called "Newcomblike" problems. We describe a new form of decision algorithm, called Timeless Decision Theory, which consistently wins on these problems.

📄 PDF Abstract BibTeX arXiv:2306.00175

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

fail 설명 없음

Similar Papers 제목 키워드 기반

Reinforcement Learning in Newcomblike Environments

2021-12-01 · NeurIPS 2021 12 · James Bell, Linda Linsefors, Caspar Oesterheld, Joar Skalse

Newcomblike decision problems have been studied extensively in the decision theory literature, but they have so far been largely absent in the reinforcement learning literature. In this paper we study value-based reinfor…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Can CDT rationalise the ex ante optimal policy via modified anthropics?

2024-11-07 · Emery Cooper, Caspar Oesterheld, Vincent Conitzer

In Newcomb's problem, causal decision theory (CDT) recommends two-boxing and thus comes apart from evidential decision theory (EDT) and ex ante policy optimisation (which prescribe one-boxing). However, in Newcomb's prob…

A review of approaches to modeling applied vehicle routing problems

2021-05-23 · Konstantin Sidorov, Alexander Morozov

Due to the practical importance of vehicle routing problems (VRP), there exists an ever-growing body of research in algorithms and (meta)heuristics for solving such problems. However, the diversity of VRP domains creates…

Diversityvalid

PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison

2022-11-29 · Hamish Flynn, David Reeb, Melih Kandemir, Jan Peters

PAC-Bayes has recently re-emerged as an effective theory with which one can derive principled learning algorithms with tight performance guarantees. However, applications of PAC-Bayes to bandit problems are relatively ra…

Decision Making

Linear Programming for Large-Scale Markov Decision Problems

2014-02-27 · Yasin Abbasi-Yadkori, Peter L. Bartlett, Alan Malek

We consider the problem of controlling a Markov decision process (MDP) with a large state space, so as to minimize average cost. Since it is intractable to compete with the optimal policy for large scale problems, we pur…