English
Related papers

Related papers: A Greedy Approximation of Bayesian Reinforcement L…

200 papers

Current music recommender systems typically act in a greedy fashion by recommending songs with the highest user ratings. Greedy recommendation, however, is suboptimal over the long term: it does not actively gather information on user…

Multimedia · Computer Science 2013-11-26 Xinxi Wang , Yi Wang , David Hsu , Ye Wang

Conveying complex objectives to reinforcement learning (RL) agents often requires meticulous reward engineering. Preference-based RL methods are able to learn a more flexible reward model based on human preferences by actively incorporating…

Machine Learning · Computer Science 2022-05-26 Xinran Liang , Katherine Shu , Kimin Lee , Pieter Abbeel

The Greedy algorithm is the simplest heuristic in sequential decision problem that carelessly takes the locally optimal choice at each round, disregarding any advantages of exploring and/or information gathering. Theoretically, it is known…

Machine Learning · Computer Science 2021-01-05 Matthieu Jedor , Jonathan Louëdec , Vianney Perchet

Bandit learning is characterized by the tension between long-term exploration and short-term exploitation. However, as has recently been noted, in settings in which the choices of the learning algorithm correspond to important decisions…

Machine Learning · Computer Science 2018-01-11 Sampath Kannan , Jamie Morgenstern , Aaron Roth , Bo Waggoner , Zhiwei Steven Wu

Offline reinforcement learning (RL) enables policy learning from static data but often suffers from poor coverage of the state-action space and distributional shift problems. This problem can be addressed by allowing limited online…

Machine Learning · Computer Science 2026-02-03 Soumyadeep Roy , Shashwat Kushwaha , Ambedkar Dukkipati

Bayesian experimental design involves the optimal allocation of resources in an experiment, with the aim of optimising cost and performance. For implicit models, where the likelihood is intractable but sampling from the model is possible,…

Machine Learning · Statistics 2019-02-26 Steven Kleinegesse , Michael Gutmann

Despite the potential of reinforcement learning (RL) for building general-purpose robotic systems, training RL agents to solve robotics tasks still remains challenging due to the difficulty of exploration in purely continuous action spaces.…

Machine Learning · Computer Science 2021-10-29 Murtaza Dalal , Deepak Pathak , Ruslan Salakhutdinov

Reinforcement learning (RL) -- algorithms that teach artificial agents to interact with environments by maximising reward signals -- has achieved significant success in recent years. These successes have been facilitated by advances in…

Machine Learning · Computer Science 2025-04-03 Llewyn Salt , Marcus Gallagher

Neural networks are powerful function approximators with tremendous potential in learning complex distributions. However, they are prone to overfitting on spurious patterns. Bayesian inference provides a principled way to regularize neural…

Machine Learning · Computer Science 2024-12-02 Yanzhe Bekkemoen , Helge Langseth

How can we efficiently gather information to optimize an unknown function, when presented with multiple, mutually dependent information sources with different costs? For example, when optimizing a robotic system, intelligently trading off…

Machine Learning · Computer Science 2018-11-05 Jialin Song , Yuxin Chen , Yisong Yue

Despite the fact that deep reinforcement learning (RL) has surpassed human-level performances in various tasks, it still has several fundamental challenges. First, most RL methods require intensive data from the exploration of the…

Machine Learning · Computer Science 2021-07-06 Zhe Xu , Bo Wu , Aditya Ojha , Daniel Neider , Ufuk Topcu

We consider the problem of diagnosing faults in a system represented by a Bayesian network, where diagnosis corresponds to recovering the most likely state of unobserved nodes given the outcomes of tests (observed nodes). Finding an optimal…

Artificial Intelligence · Computer Science 2012-07-09 Alice X. Zheng , Irina Rish , Alina Beygelzimer

Some machine learning applications require continual learning - where data comes in a sequence of datasets, each is used for training and then permanently discarded. From a Bayesian perspective, continual learning seems straightforward:…

Machine Learning · Statistics 2019-02-19 Sebastian Farquhar , Yarin Gal

Offline reinforcement learning (RL) is crucial for real-world applications where exploration can be costly or unsafe. However, offline learned policies are often suboptimal, and further online fine-tuning is required. In this paper, we…

Machine Learning · Computer Science 2024-06-03 Hao Hu , Yiqin Yang , Jianing Ye , Chengjie Wu , Ziqing Mai , Yujing Hu , Tangjie Lv , Changjie Fan , Qianchuan Zhao , Chongjie Zhang

We consider optimal sensor placement for a family of linear Bayesian inverse problems characterized by a deterministic hyper-parameter. The hyper-parameter describes distinct configurations in which measurements can be taken of the observed…

Numerical Analysis · Mathematics 2023-01-31 Nicole Aretz , Peng Chen , Denise Degen , Karen Veroy

A reciprocal LASSO (rLASSO) regularization employs a decreasing penalty function as opposed to conventional penalization approaches that use increasing penalties on the coefficients, leading to stronger parsimony and superior model…

Methodology · Statistics 2021-09-17 Himel Mallick , Rahim Alhamzawi , Erina Paul , Vladimir Svetnik

Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and informativeness to the policy. Such stable and rich…

Machine Learning · Computer Science 2021-10-28 Mete Kemertas , Tristan Aumentado-Armstrong

Model-based reinforcement learning (RL) algorithms can attain excellent sample efficiency, but often lag behind the best model-free algorithms in terms of asymptotic performance. This is especially true with high-capacity parametric…

Machine Learning · Computer Science 2018-11-05 Kurtland Chua , Roberto Calandra , Rowan McAllister , Sergey Levine

This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process. Policies are synthesised to satisfy a goal,…

Machine Learning · Computer Science 2020-03-24 Mohammadhosein Hasanbeig , Alessandro Abate , Daniel Kroening

Developments in reinforcement learning (RL) have allowed algorithms to achieve impressive performance in highly complex, but largely static problems. In contrast, biological learning seems to value efficiency of adaptation to a…

Artificial Intelligence · Computer Science 2022-05-20 Eric Chalmers , Artur Luczak