English
Related papers

Related papers: Uncertainty-sensitive Learning and Planning with E…

200 papers

This paper investigates how a Bayesian reinforcement learning method can be used to create a tactical decision-making agent for autonomous driving in an intersection scenario, where the agent can estimate the confidence of its recommended…

Robotics · Computer Science 2020-11-04 Carl-Johan Hoel , Tommy Tram , Jonas Sjöberg

Reinforcement learning (RL) systems typically optimize scalar reward functions that assume precise and reliable evaluation of outcomes. However, real-world objectives--especially those derived from human preferences--are often uncertain,…

Machine Learning · Computer Science 2026-04-30 Disha Singha

Deep learning-based support systems have demonstrated encouraging results in numerous clinical applications involving the processing of time series data. While such systems often are very accurate, they have no inherent mechanism for…

Machine Learning · Computer Science 2020-12-16 Kristoffer Wickstrøm , Karl Øyvind Mikalsen , Michael Kampffmeyer , Arthur Revhaug , Robert Jenssen

Offline reinforcement learning agents seek optimal policies from fixed data sets. With environmental interaction prohibited, agents face significant challenges in preventing errors in value estimates from compounding and subsequently…

Machine Learning · Computer Science 2023-03-28 Alex Beeson , Giovanni Montana

This paper describes a novel approach to planning which takes advantage of decision theory to greatly improve robustness in an uncertain environment. We present an algorithm which computes conditional plans of maximum expected utility. This…

Artificial Intelligence · Computer Science 2013-02-28 Stephen G. Pimentel , Lawrence M. Brem

Learned models of the environment provide reinforcement learning (RL) agents with flexible ways of making predictions about the environment. In particular, models enable planning, i.e. using more computation to improve value functions or…

Machine Learning · Computer Science 2021-10-26 Gregory Farquhar , Kate Baumli , Zita Marinho , Angelos Filos , Matteo Hessel , Hado van Hasselt , David Silver

In machine learning, an agent needs to estimate uncertainty to efficiently explore and adapt and to make effective decisions. A common approach to uncertainty estimation maintains an ensemble of models. In recent years, several approaches…

Machine Learning · Computer Science 2022-06-09 Vikranth Dwaracherla , Zheng Wen , Ian Osband , Xiuyuan Lu , Seyed Mohammad Asghari , Benjamin Van Roy

Adaptive exploration methods propose ways to learn complex policies via alternating between exploration and exploitation. An important question for such methods is to determine the appropriate moment to switch between exploration and…

Artificial Intelligence · Computer Science 2026-02-11 Leonidas Bakopoulos , Georgios Chalkiadakis

We present a new strategic voting model where we use uncertainty representation to model preferences. Specifically, we use probability sets as uncertainty representations, together with lower and upper expected utility gains to take…

Computer Science and Game Theory · Computer Science 2026-05-18 Henri Surugue , Sébastien Destercke

Deep neural networks have shown great success in prediction quality while reliable and robust uncertainty estimation remains a challenge. Predictive uncertainty supplements model predictions and enables improved functionality of downstream…

Machine Learning · Computer Science 2021-12-02 Johanna Rock , Tiago Azevedo , René de Jong , Daniel Ruiz-Muñoz , Partha Maji

In model-free deep reinforcement learning (RL) algorithms, using noisy value estimates to supervise policy evaluation and optimization is detrimental to the sample efficiency. As this noise is heteroscedastic, its effects can be mitigated…

Machine Learning · Computer Science 2022-05-04 Vincent Mai , Kaustubh Mani , Liam Paull

Estimating epistemic uncertainty in value functions is a crucial challenge for many aspects of reinforcement learning (RL), including efficient exploration, safe decision-making, and offline RL. While deep ensembles provide a robust method…

In reinforcement learning, temporal abstraction in the action space, exemplified by action repetition, is a technique to facilitate policy learning through extended actions. However, a primary limitation in previous studies of action…

Machine Learning · Computer Science 2024-02-09 Joongkyu Lee , Seung Joon Park , Yunhao Tang , Min-hwan Oh

Reinforcement learning allows solving complex tasks, however, the learning tends to be task-specific and the sample efficiency remains a challenge. We present Plan2Explore, a self-supervised reinforcement learning agent that tackles both…

Machine Learning · Computer Science 2020-07-02 Ramanan Sekar , Oleh Rybkin , Kostas Daniilidis , Pieter Abbeel , Danijar Hafner , Deepak Pathak

How to efficiently explore in reinforcement learning is an open problem. Many exploration algorithms employ the epistemic uncertainty of their own value predictions -- for instance to compute an exploration bonus or upper confidence bound.…

Machine Learning · Computer Science 2023-03-08 Simon Schmitt , John Shawe-Taylor , Hado van Hasselt

An important property for lifelong-learning agents is the ability to combine existing skills to solve unseen tasks. In general, however, it is unclear how to compose skills in a principled way. We provide a "recipe" for optimal value…

Machine Learning · Computer Science 2018-07-13 Benjamin van Niekerk , Steven James , Adam Earle , Benjamin Rosman

Heterogeneous ensembles built from the predictions of a wide variety and large number of diverse base predictors represent a potent approach to building predictive models for problems where the ideal base/individual predictor may not be…

Machine Learning · Computer Science 2021-03-01 Ana Stanescu , Gaurav Pandey

Solving tasks with sparse rewards is one of the most important challenges in reinforcement learning. In the single-agent setting, this challenge is addressed by introducing intrinsic rewards that motivate agents to explore unseen regions of…

Machine Learning · Computer Science 2021-05-25 Shariq Iqbal , Fei Sha

Reinforcement learning (RL) methods have been shown to be capable of learning intelligent behavior in rich domains. However, this has largely been done in simulated domains without adequate focus on the process of building the simulator. In…

Machine Learning · Computer Science 2019-10-24 Aditya Modi , Nan Jiang , Ambuj Tewari , Satinder Singh

Deep learning has emerged as a promising paradigm to give access to highly accurate predictions of molecular and materials properties. A common short-coming shared by current approaches, however, is that neural networks only give point…

Computational Physics · Physics 2023-05-10 Albert Zhu , Simon Batzner , Albert Musaelian , Boris Kozinsky