paper-with-me

홈 › Papers

Approximate information for efficient exploration-exploitation strategies

2023-07-04 · Alex Barbier-Chebbah, Christian L. Vestergaard, Jean-Baptiste Masson

This paper addresses the exploration-exploitation dilemma inherent in decision-making, focusing on multi-armed bandit problems. The problems involve an agent deciding whether to exploit current knowledge for immediate gains or explore new avenues for potential long-term rewards. We here introduce a novel algorithm, approximate information maximization (AIM), which employs an analytical approximation of the entropy gradient to choose which arm to pull at each point in time. AIM matches the performance of Infomax and Thompson sampling while also offering enhanced computational speed, determinism, and tractability. Empirical evaluation of AIM indicates its compliance with the Lai-Robbins asymptotic bound and demonstrates its robustness for a range of priors. Its expression is tunable, which allows for specific optimization in various settings.

📄 PDF Abstract BibTeX arXiv:2307.01563

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingEfficient ExplorationThompson Sampling

Similar Papers 제목 키워드 기반

Dynamic Exploration-Exploitation Trade-Off in Active Learning Regression with Bayesian Hierarchical Modeling

2023-04-16 · Upala Junaida Islam, Kamran Paynabar, George Runger, Ashif Sikandar Iquebal

Active learning provides a framework to adaptively query the most informative experiments towards learning an unknown black-box function. Various approaches of active learning have been proposed in the literature, howeve…

Active Learningregression

Dealing with uncertainty: balancing exploration and exploitation in deep recurrent reinforcement learning

2023-10-12 · Valentina Zangirolami, Matteo Borrotti

Incomplete knowledge of the environment leads an agent to make decisions under uncertainty. One of the major dilemmas in Reinforcement Learning (RL) where an autonomous agent has to balance two contrasting needs in makin…

Autonomous Drivingreinforcement-learningReinforcement Learning (RL)

Dual Control for Approximate Bayesian Reinforcement Learning

2015-10-13 · Edgar D. Klenske, Philipp Hennig

Control of non-episodic, finite-horizon dynamical systems with uncertain dynamics poses a tough and elementary case of the exploration-exploitation trade-off. Bayesian reinforcement learning, reasoning about the effect o…

regressionreinforcement-learningReinforcement LearningReinforcement Learning (RL)

$φ$-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation

2025-03-17 · Fangzhi Xu, Hang Yan, Chang Ma, Haiteng Zhao 외

Inference-time optimization scales computation to derive deliberate reasoning steps for effective performance. While previous search-based strategies address the short-sightedness of auto-regressive generation, the vast …

Infomax strategies for an optimal balance between exploration and exploitation

2016-01-12 · Gautam Reddy, Antonio Celani, Massimo Vergassola

Proper balance between exploitation and exploration is what makes good decisions, which achieve high rewards like payoff or evolutionary fitness. The Infomax principle postulates that maximization of information directs …