English
Related papers

Related papers: Implicit Updates for Average-Reward Temporal Diffe…

200 papers

In reinforcement learning (RL), temporal difference (TD) errors are widely adopted for optimizing value and policy functions. However, since the TD error is defined by a bootstrap method, its computation tends to be noisy and destabilize…

Machine Learning · Computer Science 2026-04-03 Taisuke Kobayashi

Estimating value functions is a core component of reinforcement learning algorithms. Temporal difference (TD) learning algorithms use bootstrapping, i.e. they update the value function toward a learning target using value estimates at…

Machine Learning · Computer Science 2022-01-07 Anthony GX-Chen , Veronica Chelu , Blake A. Richards , Joelle Pineau

Anomaly detection in time series data is important for applications in finance, healthcare, sensor networks, and industrial monitoring. Traditional methods usually struggle with limited labeled data, high false-positive rates, and…

Machine Learning · Computer Science 2025-09-01 Bahareh Golchin , Banafsheh Rekabdar , Kunpeng Liu

In reinforcement learning, the discount factor $\gamma$ controls the agent's effective planning horizon. Traditionally, this parameter was considered part of the MDP; however, as deep reinforcement learning algorithms tend to become…

Machine Learning · Computer Science 2020-06-24 Chen Tessler , Shie Mannor

Rewards play an essential role in reinforcement learning. In contrast to rule-based game environments with well-defined reward functions, complex real-world robotic applications, such as contact-rich manipulation, lack explicit and…

Machine Learning · Computer Science 2022-05-30 Yuning Wu , Jieliang Luo , Hui Li

Early stopping based on the validation set performance is a popular approach to find the right balance between under- and overfitting in the context of supervised learning. However, in reinforcement learning, even for supervised…

Machine Learning · Computer Science 2023-03-20 Nicolai Dorka , Tim Welschehold , Wolfram Burgard

We address the problem of policy evaluation in discounted Markov decision processes, and provide instance-dependent guarantees on the $\ell_\infty$-error under a generative model. We establish both asymptotic and non-asymptotic versions of…

Machine Learning · Statistics 2020-03-17 Koulik Khamaru , Ashwin Pananjady , Feng Ruan , Martin J. Wainwright , Michael I. Jordan

Many value-based deep reinforcement learning algorithms rely on target networks - lagged copies of the online network - to stabilize training. While effective, this mechanism introduces a fundamental stability-recency tradeoff: slower…

Machine Learning · Computer Science 2026-05-20 Leonard S. Pleiss , James Harrison , Maximilian Schiffer

In reinforcement learning, two objective functions have been developed extensively in the literature: discounted and averaged rewards. The generalization to an entropy-regularized setting has led to improved robustness and exploration for…

Machine Learning · Computer Science 2025-01-20 Jacob Adamczyk , Volodymyr Makarenko , Stas Tiomkin , Rahul V. Kulkarni

Machine learning models are prone to capturing the spurious correlations between non-causal attributes and classes, with counterfactual data augmentation being a promising direction for breaking these spurious associations. However,…

Machine Learning · Computer Science 2025-07-11 Xiaoling Zhou , Ou Wu , Michael K. Ng

We provide non-asymptotic bounds for the well-known temporal difference learning algorithm TD(0) with linear function approximators. These include high-probability bounds as well as bounds in expectation. Our analysis suggests that a…

Machine Learning · Computer Science 2015-09-02 Nathaniel Korda , L. A. Prashanth

Correlated outcomes are common in many practical problems. In some settings, one outcome is of particular interest, and others are auxiliary. To leverage information shared by all the outcomes, traditional multi-task learning (MTL)…

Methodology · Statistics 2023-03-23 Muxuan Liang , Jaeyoung Park , Qing Lu , Xiang Zhong

Reinforcement Learning (RL) has proven highly effective in aligning Large Language Models (LLMs) with human preferences. Typical RL methods optimize under an overall sequence reward, which can lead to a suboptimal learning process. This…

Machine Learning · Computer Science 2025-02-26 Yanshi Li , Shaopan Xiong , Gengru Chen , Xiaoyang Li , Yijia Luo , Xingyuan Bu , Yingshui Tan , Wenbo Su , Bo Zheng

The focus of this paper is on stochastic variational inequalities (VI) under Markovian noise. A prominent application of our algorithmic developments is the stochastic policy evaluation problem in reinforcement learning. Prior…

Optimization and Control · Mathematics 2021-08-17 Georgios Kotsalis , Guanghui Lan , Tianjiao Li

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…

Machine Learning models in real-world applications must continuously learn new tasks to adapt to shifts in the data-generating distribution. Yet, for Continual Learning (CL), models often struggle to balance learning new tasks (plasticity)…

Machine Learning · Computer Science 2025-10-24 Luckeciano C. Melo , Alessandro Abate , Yarin Gal

We study the multi-step off-policy learning approach to distributional RL. Despite the apparent similarity between value-based RL and distributional RL, our study reveals intriguing and fundamental differences between the two cases in the…

Machine Learning · Computer Science 2022-07-18 Yunhao Tang , Mark Rowland , Rémi Munos , Bernardo Ávila Pires , Will Dabney , Marc G. Bellemare

Random delays weaken the temporal correspondence between actions and subsequent state feedback, making it difficult for agents to identify the true propagation process of action effects. In cross-task scenarios, changes in task objectives…

Machine Learning · Computer Science 2026-05-13 Chenran Zhao , Dianxi Shi , Yaowen Zhang , Chunping Qiu , Shaowu Yang

Motivated by applications in risk-sensitive reinforcement learning, we study mean-variance optimization in a discounted reward Markov Decision Process (MDP). Specifically, we analyze a Temporal Difference (TD) learning algorithm with linear…

Machine Learning · Computer Science 2025-03-13 Tejaram Sangadi , L. A. Prashanth , Krishna Jagannathan

Epistemic uncertainty quantification is a crucial part of drawing credible conclusions from predictive models, whether concerned about the prediction at a given point or any downstream evaluation that uses the model as input. When the…

Machine Learning · Statistics 2022-11-15 Nathan Kallus , James McInerney