English
Related papers

Related papers: AWD3: Dynamic Reduction of the Estimation Bias

200 papers

Example weighting algorithm is an effective solution to the training bias problem, however, most previous typical methods are usually limited to human knowledge and require laborious tuning of hyperparameters. In this paper, we propose a…

Machine Learning · Computer Science 2019-11-27 Zhenmao Li , Yichao Wu , Ken Chen , Yudong Wu , Shunfeng Zhou , Jiaheng Liu , Junjie Yan

We propose a policy improvement algorithm for Reinforcement Learning (RL) which is called Rerouted Behavior Improvement (RBI). RBI is designed to take into account the evaluation errors of the Q-function. Such errors are common in RL when…

Machine Learning · Computer Science 2019-07-12 Elad Sarafian , Aviv Tamar , Sarit Kraus

Reinforcement learning (RL) algorithms update an agent's parameters according to one of several possible rules, discovered manually through years of research. Automating the discovery of update rules from data could lead to more efficient…

Machine Learning · Computer Science 2021-01-06 Junhyuk Oh , Matteo Hessel , Wojciech M. Czarnecki , Zhongwen Xu , Hado van Hasselt , Satinder Singh , David Silver

Sample inefficiency is a long-lasting challenge in deep reinforcement learning (DRL). Despite dramatic improvements have been made, the problem is far from being solved and is especially challenging in environments with sparse or delayed…

Machine Learning · Computer Science 2025-06-17 Federico Malato , Ville Hautamaki

Majority of off-policy reinforcement learning algorithms use overestimation bias control techniques. Most of these techniques rooted in heuristics, primarily addressing the consequences of overestimation rather than its fundamental origins.…

Machine Learning · Computer Science 2023-09-27 Arsenii Kuznetsov

We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms. The idea is to evolve a differentiable loss function, such that an agent, which optimizes its policy to minimize this loss, will achieve…

Machine Learning · Computer Science 2018-05-01 Rein Houthooft , Richard Y. Chen , Phillip Isola , Bradly C. Stadie , Filip Wolski , Jonathan Ho , Pieter Abbeel

Experience replay (ER) is a fundamental component of off-policy deep reinforcement learning (RL). ER recalls experiences from past iterations to compute gradient estimates for the current policy, increasing data-efficiency. However, the…

Machine Learning · Computer Science 2019-05-21 Guido Novati , Petros Koumoutsakos

We study estimation and inference using data collected by reinforcement learning (RL) algorithms. These algorithms adaptively experiment by interacting with individual units over multiple stages, updating their strategies based on past…

Machine Learning · Statistics 2025-10-06 Vasilis Syrgkanis , Ruohan Zhan

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates are performed on data collected by older policies. This…

Machine Learning · Computer Science 2026-05-28 Otmane Sakhi , Aleksei Arzhantsev , Imad Aouali , Flavian Vasile

Many off-policy prediction learning algorithms have been proposed in the past decade, but it remains unclear which algorithms learn faster than others. We empirically compare 11 off-policy prediction learning algorithms with linear function…

Machine Learning · Computer Science 2021-09-14 Sina Ghiassian , Richard S. Sutton

Experience replay enables off-policy reinforcement learning (RL) agents to utilize past experiences to maximize the cumulative reward. Prioritized experience replay that weighs experiences by the magnitude of their temporal-difference error…

Machine Learning · Computer Science 2021-02-08 Ang A. Li , Zongqing Lu , Chenglin Miao

The optimal objective is a fundamental aspect of reinforcement learning (RL), as it determines how policies are evaluated and optimized. While total return maximization is the ideal objective in RL, discounted return maximization is the…

Machine Learning · Computer Science 2025-03-19 Shuyu Yin , Fei Wen , Peilin Liu , Tao Luo

Deep learning systems are known to exhibit implicit regularization (alt. implicit bias), favoring simple solutions instead of merely minimizing the loss function. In some cases, we can analytically derive the implicit regularization --…

Machine Learning · Statistics 2026-05-08 Joseph H. Rudoler , Kevin Tan , Giles Hooker , Konrad P. Kording

Reinforcement learning (RL) provides an appealing formalism for learning control policies from experience. However, the classic active formulation of RL necessitates a lengthy active exploration process for each behavior, making it…

Machine Learning · Computer Science 2021-04-27 Ashvin Nair , Abhishek Gupta , Murtaza Dalal , Sergey Levine

The policy represented by the deep neural network can overfit the spurious features in observations, which hamper a reinforcement learning agent from learning effective policy. This issue becomes severe in high-dimensional state, where the…

Machine Learning · Computer Science 2023-05-01 Md Masudur Rahman , Yexiang Xue

We address the issue of estimation bias in deep reinforcement learning (DRL) by introducing solution mechanisms that include a new, twin TD-regularized actor-critic (TDR) method. It aims at reducing both over and under-estimation errors.…

Machine Learning · Computer Science 2023-11-08 Junmin Zhong , Ruofan Wu , Jennie Si

One of the most basic problems in reinforcement learning (RL) is policy evaluation: estimating the long-term return, i.e., value function, corresponding to a given fixed policy. The celebrated Temporal Difference (TD) learning algorithm…

Machine Learning · Computer Science 2025-02-10 Sreejeet Maity , Aritra Mitra

Deep Reinforcement Learning (RL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. To alleviate this issue, we propose to exploit the symmetries…

Robotics · Computer Science 2020-08-27 Yijiong Lin , Jiancong Huang , Matthieu Zimmer , Yisheng Guan , Juan Rojas , Paul Weng

Offline imitation learning enables learning a policy solely from a set of expert demonstrations, without any environment interaction. To alleviate the issue of distribution shift arising due to the small amount of expert data, recent works…

Machine Learning · Computer Science 2025-05-23 Udita Ghosh , Dripta S. Raychaudhuri , Jiachen Li , Konstantinos Karydis , Amit K. Roy-Chowdhury

Q-Learning is a fundamental off-policy reinforcement learning (RL) algorithm that has the objective of approximating action-value functions in order to learn optimal policies. Nonetheless, it has difficulties in reconciling bias with…

Machine Learning · Computer Science 2024-11-22 Mahammad Humayoo