paper-with-me

Papers

Exploration by Optimisation in Partial Monitoring

2019-07-12 · Tor Lattimore, Csaba Szepesvari

We provide a simple and efficient algorithm for adversarial $k$-action $d$-outcome non-degenerate locally observable partial monitoring game for which the $n$-round minimax regret is bounded by $6(d+1) k^{3/2} \sqrt{n \log(k)}$, matching the best known information-theoretic upper bound. The same algorithm also achieves near-optimal regret for full information, bandit and globally observable games.

📄 PDF Abstract BibTeX arXiv:1907.05772

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bayesian Exploration Networks

2023-08-24 · Mattie Fellows, Brandon Kaplowitz, Christian Schroeder de Witt, Shimon Whiteson

Bayesian reinforcement learning (RL) offers a principled and elegant approach for sequential decision making under uncertainty. Most notably, Bayesian agents do not face an exploration/exploitation dilemma, a major patho…

Decision MakingDecision Making Under UncertaintyDensity EstimationNormalising Flows+3

Applying Partial-ACO to Large-scale Vehicle Fleet Optimisation

2019-04-16 · Darren M. Chitty, Elizabeth Wanner, Rakhi Parmar, Peter R. Lewis

Optimisation of fleets of commercial vehicles with regards scheduling tasks from various locations to vehicles can result in considerably lower fleet traversal times. This has significant benefits including reduced expen…

Scheduling

Beyond Optimism: Exploration With Partially Observable Rewards

2024-06-20 · Simone Parisi, Alireza Kazemipour, Michael Bowling

Exploration in reinforcement learning (RL) remains an open challenge. RL algorithms rely on observing rewards to train the agent, and if informative rewards are sparse the agent learns slowly or may not learn at all. To …

BenchmarkingReinforcement Learning (RL)

Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring

2025-10-22 · Federico Di Gennaro, Khaled Eldowa, Nicolò Cesa-Bianchi arxiv

In contrast to the classic formulation of partial monitoring, linear partial monitoring can model infinite outcome spaces, while imposing a linear structure on both the losses and the observations. This setting can be vi…

MAGPIE: Machine Automated General Performance Improvement via Evolution of Software

2022-08-04 · Aymeric Blot, Justyna Petke

Performance is one of the most important qualities of software. Several techniques have thus been proposed to improve it, such as program transformations, optimisation of software parameters, or compiler flags. Many auto…