English
Related papers

Related papers: In Hindsight: A Smooth Reward for Steady Explorati…

200 papers

Recent advancements in state-of-the-art (SOTA) offline reinforcement learning (RL) have primarily focused on addressing function approximation errors, which contribute to the overestimation of Q-values for out-of-distribution actions, a…

Machine Learning · Computer Science 2025-05-01 Pulkit Agrawal , Rukma Talwadker , Aditya Pareek , Tridib Mukherjee

We prove performance guarantees of two algorithms for approximating $Q^\star$ in batch reinforcement learning. Compared to classical iterative methods such as Fitted Q-Iteration---whose performance loss incurs quadratic dependence on…

Machine Learning · Computer Science 2020-08-25 Tengyang Xie , Nan Jiang

We study the problem of temporal-difference-based policy evaluation in reinforcement learning. In particular, we analyse the use of a distributional reinforcement learning algorithm, quantile temporal-difference learning (QTD), for this…

Machine Learning · Computer Science 2023-05-31 Mark Rowland , Yunhao Tang , Clare Lyle , Rémi Munos , Marc G. Bellemare , Will Dabney

Real-time heuristic search is a popular model of acting and learning in intelligent autonomous agents. Learning real-time search agents improve their performance over time by acquiring and refining a value function guiding the application…

Artificial Intelligence · Computer Science 2007-05-23 Vadim Bulitko

Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time. Existing infinite-horizon methods, which often rely on discounted…

Machine Learning · Computer Science 2026-02-03 Jiamin Xu , Kyra Gan

Reinforcement learning is a general technique that allows an agent to learn an optimal policy and interact with an environment in sequential decision making problems. The goodness of a policy is measured by its value function starting from…

Machine Learning · Statistics 2025-06-30 C. Shi , S. Zhang , W. Lu , R. Song

Recent methods for imitation learning directly learn a $Q$-function using an implicit reward formulation rather than an explicit reward function. However, these methods generally require implicit reward regularization to improve stability…

Machine Learning · Computer Science 2023-03-02 Firas Al-Hafez , Davide Tateo , Oleg Arenz , Guoping Zhao , Jan Peters

An effective approach to exploration in reinforcement learning is to rely on an agent's uncertainty over the optimal policy, which can yield near-optimal exploration strategies in tabular settings. However, in non-tabular settings that…

Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as to…

Machine Learning · Computer Science 2021-10-13 Ilya Kostrikov , Ashvin Nair , Sergey Levine

This paper studies offline reinforcement learning with linear function approximation in a setting with decision-theoretic, but not estimation sparsity. The structural restrictions of the data-generating process presume that the transitions…

Machine Learning · Statistics 2024-01-24 Angela Zhou

Q-learning (QL), a common reinforcement learning algorithm, suffers from over-estimation bias due to the maximization term in the optimal Bellman operator. This bias may lead to sub-optimal behavior. Double-Q-learning tackles this issue by…

Machine Learning · Computer Science 2021-04-21 Oren Peer , Chen Tessler , Nadav Merlis , Ron Meir

This paper develops a sign-separated finite-time error analysis for constant step-size Q-learning. Starting from the switching-system representation, the error is decomposed into its componentwise negative and positive parts. The negative…

Artificial Intelligence · Computer Science 2026-05-18 Donghwan Lee

Commonly in reinforcement learning (RL), rewards are discounted over time using an exponential function to model time preference, thereby bounding the expected long-term reward. In contrast, in economics and psychology, it has been shown…

Machine Learning · Computer Science 2022-12-08 Matthias Schultheis , Constantin A. Rothkopf , Heinz Koeppl

Advantage learning (AL) aims to improve the robustness of value-based reinforcement learning against estimation errors with action-gap-based regularization. Unfortunately, the method tends to be unstable in the case of function…

Machine Learning · Computer Science 2022-03-22 Yaozhong Gan , Zhe Zhang , Xiaoyang Tan

By reusing data throughout training, off-policy deep reinforcement learning algorithms offer improved sample efficiency relative to on-policy approaches. For continuous action spaces, the most popular methods for off-policy learning include…

Machine Learning · Computer Science 2023-12-01 Jared Markowitz , Jesse Silverberg , Gary Collins

Reinforcement learning (RL) typically defines a discount factor as part of the Markov Decision Process. The discount factor values future rewards by an exponential scheme that leads to theoretical convergence guarantees of the Bellman…

Machine Learning · Statistics 2019-03-01 William Fedus , Carles Gelada , Yoshua Bengio , Marc G. Bellemare , Hugo Larochelle

We consider the off-policy evaluation problem of reinforcement learning using deep convolutional neural networks. We analyze the deep fitted Q-evaluation method for estimating the expected cumulative reward of a target policy, when the data…

Machine Learning · Computer Science 2022-10-05 Xiang Ji , Minshuo Chen , Mengdi Wang , Tuo Zhao

The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can…

Machine Learning · Computer Science 2015-12-10 Hado van Hasselt , Arthur Guez , David Silver

Sample complexity bounds are a common performance metric in the Reinforcement Learning literature. In the discounted cost, infinite horizon setting, all of the known bounds have a factor that is a polynomial in $1/(1-\gamma)$, where $\gamma…

Machine Learning · Computer Science 2020-07-09 Adithya M. Devraj , Sean P. Meyn

In value-based deep reinforcement learning methods, approximation of value functions induces overestimation bias and leads to suboptimal policies. We show that in deep actor-critic methods that aim to overcome the overestimation bias, if…

Machine Learning · Computer Science 2021-12-28 Baturay Saglam , Enes Duran , Dogan C. Cicek , Furkan B. Mutlu , Suleyman S. Kozat