English
Related papers

Related papers: Demystifying the Recency Heuristic in Temporal-Dif…

200 papers

Temporal difference learning with linear function approximation is a popular method to obtain a low-dimensional approximation of the value function of a policy in a Markov Decision Process. We give a new interpretation of this method in…

Machine Learning · Computer Science 2020-10-29 Rui Liu , Alex Olshevsky

A misspecified reward can degrade sample efficiency and induce undesired behaviors in reinforcement learning (RL) problems. We propose symbolic reward machines for incorporating high-level task knowledge when specifying the reward signals.…

Artificial Intelligence · Computer Science 2022-04-22 Weichao Zhou , Wenchao Li

Hierarchical methods in reinforcement learning have the potential to reduce the amount of decisions that the agent needs to perform when learning new tasks. However, finding reusable useful temporal abstractions that facilitate fast…

Machine Learning · Computer Science 2023-04-05 David Kuric , Herke van Hoof

In this work, we provide theoretical guarantees for reward decomposition in deterministic MDPs. Reward decomposition is a special case of Hierarchical Reinforcement Learning, that allows one to learn many policies in parallel and combine…

Machine Learning · Computer Science 2018-03-14 Tom Zahavy , Avinatan Hasidim , Haim Kaplan , Yishay Mansour

Modern deep reinforcement learning methods have departed from the incremental learning required for eligibility traces, rendering the implementation of the $\lambda$-return difficult in this context. In particular, off-policy methods that…

Machine Learning · Computer Science 2020-01-15 Brett Daley , Christopher Amato

In reinforcement learning, the TD($\lambda$) algorithm is a fundamental policy evaluation method with an efficient online implementation that is suitable for large-scale problems. One practical drawback of TD($\lambda$) is its sensitivity…

Machine Learning · Statistics 2014-12-23 Aviv Tamar , Panos Toulis , Shie Mannor , Edoardo M. Airoldi

Reinforcement learning from verifiable rewards (RLVR) has emerged as a central technique for improving the reasoning capabilities of large language models. Despite its effectiveness, how response-level rewards translate into token-level…

Machine Learning · Computer Science 2026-05-21 Kaiyi Zhang , Wei Wu , Yankai Lin

Reinforcement Learning (RL) has shown promise for aligning Large Language Models (LLMs) to follow instructions with various constraints. Despite the encouraging results, RL improvement inevitably relies on sampling successful, high-quality…

Artificial Intelligence · Computer Science 2025-12-30 Kongcheng Zhang , Qi Yao , Shunyu Liu , Wenjian Zhang , Min Cen , Yang Zhou , Wenkai Fang , Yiru Zhao , Baisheng Lai , Mingli Song

Respondent-driven sampling (RDS) is widely used to study hidden or hard-to-reach populations by incentivizing study participants to recruit their social connections. The success and efficiency of RDS can depend critically on the nature of…

Methodology · Statistics 2025-01-06 Justin Weltz , Angela Yoon , Yichi Zhang , Alexander Volfovsky , Eric Laber

Time-dependent data-generating distributions have proven to be difficult for gradient-based training of neural networks, as the greedy updates result in catastrophic forgetting of previously learned knowledge. Despite the progress in the…

Machine Learning · Computer Science 2023-04-03 Matthias De Lange , Gido van de Ven , Tinne Tuytelaars

Reward design in reinforcement learning and optimal control is challenging. Preference-based alignment addresses this by enabling agents to learn rewards from ranked trajectory pairs provided by humans. However, existing methods often…

Machine Learning · Computer Science 2025-05-29 Zhixian Xie , Haode Zhang , Yizhe Feng , Wanxin Jin

The capability to widely sample the state and action spaces is a key ingredient toward building effective reinforcement learning algorithms. The variational optimization principles exposed in this paper emphasize the importance of an…

Machine Learning · Computer Science 2022-05-25 Emmanuel Daucé

Reinforcement learning from human feedback (RLHF) offers a promising approach to aligning large language models (LLMs) with human preferences. Typically, a reward model is trained or supplied to act as a proxy for humans in evaluating…

Computation and Language · Computer Science 2025-09-12 Jiahui Li , Lin Li , Tai-wei Chang , Kun Kuang , Long Chen , Jun Zhou , Cheng Yang

The central tenet of reinforcement learning (RL) is that agents seek to maximize the sum of cumulative rewards. In contrast, active inference, an emerging framework within cognitive and computational neuroscience, proposes that agents act…

Machine Learning · Computer Science 2020-03-02 Alexander Tschantz , Beren Millidge , Anil K. Seth , Christopher L. Buckley

Multi-task reinforcement learning (RL) aims to simultaneously learn policies for solving many tasks. Several prior works have found that relabeling past experience with different reward functions can improve sample efficiency. Relabeling…

Machine Learning · Computer Science 2020-02-26 Benjamin Eysenbach , Xinyang Geng , Sergey Levine , Ruslan Salakhutdinov

The ability to estimate temporal relationships is critical for both animals and artificial agents. Cognitive science and neuroscience provide remarkable insights into behavioral and neural aspects of temporal credit assignment. In…

Artificial Intelligence · Computer Science 2024-12-23 Md Rysul Kabir , James Mochizuki-Freeman , Zoran Tiganj

Temporal difference (TD) learning is often used to update the estimate of the value function which is used by RL agents to extract useful policies. In this paper, we focus on value function estimation in continual reinforcement learning. We…

Machine Learning · Computer Science 2023-12-20 Nishanth Anand , Doina Precup

Hierarchical reinforcement learning (HRL) has seen widespread interest as an approach to tractable learning of complex modular behaviors. However, existing work either assume access to expert-constructed hierarchies, or use…

Machine Learning · Computer Science 2021-10-19 Kurtland Chua , Qi Lei , Jason D. Lee

Temporal credit assignment is crucial for learning and skill development in natural and artificial intelligence. While computational methods like the TD approach in reinforcement learning have been proposed, it's unclear if they accurately…

Artificial Intelligence · Computer Science 2023-07-18 Thuy Ngoc Nguyen , Chase McDonald , Cleotilde Gonzalez

We consider the core reinforcement-learning problem of on-policy value function approximation from a batch of trajectory data, and focus on various issues of Temporal Difference (TD) learning and Monte Carlo (MC) policy evaluation. The two…