English
Related papers

Related papers: Robbins-Monro conditions for persistent exploratio…

200 papers

Reinforcement Learning is a powerful tool to model decision-making processes. However, it relies on an exploration-exploitation trade-off that remains an open challenge for many tasks. In this work, we study neighboring state-based,…

Machine Learning · Computer Science 2025-11-04 Yu-Teng Li , Justin Lin , Jeffery Cheng , Pedro Pachuca

How do you incentivize self-interested agents to $\textit{explore}$ when they prefer to $\textit{exploit}$? We consider complex exploration problems, where each agent faces the same (but unknown) MDP. In contrast with traditional…

Machine Learning · Computer Science 2023-02-21 Max Simchowitz , Aleksandrs Slivkins

We consider a class of reinforcement-learning systems in which the agent follows a behavior policy to explore a discrete state-action space to find an optimal policy while adhering to some restriction on its behavior. Such restriction may…

Machine Learning · Computer Science 2023-04-07 Peter C. Y. Chen

Motivated by the prevailing paradigm of using unsupervised learning for efficient exploration in reinforcement learning (RL) problems [tang2017exploration,bellemare2016unifying], we investigate when this paradigm is provably efficient. We…

Machine Learning · Computer Science 2020-12-02 Fei Feng , Ruosong Wang , Wotao Yin , Simon S. Du , Lin F. Yang

We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions, i.e. environments more general than (PO)MDPs. The task for an agent is to attain…

Machine Learning · Computer Science 2009-12-30 Daniil Ryabko , Marcus Hutter

We provide a framework for speeding up algorithms for time-bounded reachability analysis of continuous-time Markov decision processes. The principle is to find a small, but almost equivalent subsystem of the original system and only analyse…

Systems and Control · Computer Science 2018-07-26 Pranav Ashok , Yuliya Butkova , Holger Hermanns , Jan Křetínský

We introduce a restricted latent class exploratory model for longitudinal data with ordinal attributes and respondent-specific covariates. Responses follow a time inhomogeneous hidden Markov model where the probability of a respondent's…

Methodology · Statistics 2026-03-11 Eric Alan Wayman , Steven Andrew Culpepper , Jeff Douglas , Jesse Bowers

The question of how to explore, i.e., take actions with uncertain outcomes to learn about possible future rewards, is a key question in reinforcement learning (RL). Here, we show a surprising result: We show that Q-learning with nonlinear…

Machine Learning · Computer Science 2018-05-31 Justas Dauparas , Ryota Tomioka , Katja Hofmann

Reinforcement learning with sparse rewards is still an open challenge. Classic methods rely on getting feedback via extrinsic rewards to train the agent, and in situations where this occurs very rarely the agent learns slowly or cannot…

Machine Learning · Computer Science 2022-03-04 Simone Parisi , Davide Tateo , Maximilian Hensel , Carlo D'Eramo , Jan Peters , Joni Pajarinen

Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to…

Machine Learning · Computer Science 2018-07-06 Fabio Pardo , Vitaly Levdik , Petar Kormushev

While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward. Although the agent will…

Machine Learning · Computer Science 2020-07-16 Evrard Garcelon , Mohammad Ghavamzadeh , Alessandro Lazaric , Matteo Pirotta

Robust reinforcement learning is essential for deploying reinforcement learning algorithms in real-world scenarios where environmental uncertainty predominates. Traditional robust reinforcement learning often depends on rectangularity…

Machine Learning · Computer Science 2024-06-13 Adil Zouitine , David Bertoin , Pierre Clavier , Matthieu Geist , Emmanuel Rachelson

The Robbins-Monro algorithm is a recursive, simulation-based stochastic procedure to approximate the zeros of a function that can be written as an expectation. It is known that under some technical assumptions, a Gaussian convergence can be…

Probability · Mathematics 2025-10-17 Lorick Huang , V Konakov

We present the convergence rates of synchronous and asynchronous Q-learning for average-reward Markov decision processes, where the absence of contraction poses a fundamental challenge. Existing non-asymptotic results overcome this…

Machine Learning · Computer Science 2026-01-30 Zijun Chen , Zaiwei Chen , Nian Si , Shengbo Wang

We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments, where the task may change over time. While RNN-based policies could in principle represent such strategies, in practice…

We propose an exploration method that incorporates look-ahead search over basic learnt skills and their dynamics, and use it for reinforcement learning (RL) of manipulation policies . Our skills are multi-goal policies learned in isolation…

Robotics · Computer Science 2018-11-21 Arpit Agarwal , Katharina Muelling , Katerina Fragkiadaki

Reinforcement learning (RL) is a powerful framework for decision-making in uncertain environments, but it often requires large amounts of data to learn an optimal policy. We address this challenge by incorporating prior model knowledge to…

Machine Learning · Computer Science 2026-01-29 J. S. van Hulst , W. P. M. H. Heemels , D. J. Antunes

In this paper we consider the problem of how a reinforcement learning agent that is tasked with solving a sequence of reinforcement learning problems (a sequence of Markov decision processes) can use knowledge acquired early in its lifetime…

Machine Learning · Computer Science 2019-02-05 Francisco M. Garcia , Philip S. Thomas

Reinforcement learning systems are often concerned with balancing exploration of untested actions against exploitation of actions that are known to be good. The benefit of exploration can be estimated using the classical notion of Value of…

Artificial Intelligence · Computer Science 2013-01-30 Richard Dearden , Nir Friedman , David Andre

Many potential applications of reinforcement learning (RL) are stymied by the large numbers of samples required to learn an effective policy. This is especially true when applying RL to real-world control tasks, e.g. in the sciences or…

Machine Learning · Computer Science 2022-10-11 Viraj Mehta , Ian Char , Joseph Abbate , Rory Conlin , Mark D. Boyer , Stefano Ermon , Jeff Schneider , Willie Neiswanger