English
Related papers

Related papers: Variance Reduced Advantage Estimation with $\delta…

200 papers

This work focuses on the dynamic hedging of financial derivatives, where a reinforcement learning algorithm is designed to minimize the variance of the delta hedging process. In contrast to previous research in this area, we apply…

Optimization and Control · Mathematics 2023-06-21 Cong Zheng , Jiafa He , Can Yang

Training data attribution (TDA) provides insights into which training data is responsible for a learned model behavior. Gradient-based TDA methods such as influence functions and unrolled differentiation both involve a computation that…

Machine Learning · Computer Science 2025-07-22 Andrew Wang , Elisa Nguyen , Runshi Yang , Juhan Bae , Sheila A. McIlraith , Roger Grosse

Reinforcement learning has become a cornerstone technique for developing reasoning models in complex tasks, ranging from mathematical problem-solving to imaginary reasoning. The optimization of these models typically relies on policy…

Machine Learning · Computer Science 2026-02-11 Qingnan Ren , Shiting Huang , Zhen Fang , Zehui Chen , Lin Chen , Lijun Li , Feng Zhao

Optimizing large language models for industrial sales requires balancing long-term commercial objectives (e.g., conversion rate) with immediate linguistic constraints such as fluency and compliance. Conventional reinforcement learning often…

Artificial Intelligence · Computer Science 2026-03-03 Haojin Yang , Ai Jian , Xinyue Huang , Yiwei Wang , Weipeng Zhang , Ke Zeng , Xunliang Cai , Jingqing Ruan

Any reinforcement learning system must be able to identify which past events contributed to observed outcomes, a problem known as credit assignment. A common solution to this problem is to use an eligibility trace to assign credit to…

Machine Learning · Computer Science 2022-07-26 Duncan Bailey , Marcelo G. Mattar

We consider the large sum of DC (Difference of Convex) functions minimization problem which appear in several different areas, especially in stochastic optimization and machine learning. Two DCA (DC Algorithm) based algorithms are proposed:…

Optimization and Control · Mathematics 2019-11-12 Hoai An Le Thi , Hoai Minh Le , Duy Nhat Phan , Bach Tran

Hierarchical Reinforcement Learning (HRL) has held longstanding promise to advance reinforcement learning. Yet, it has remained a considerable challenge to develop practical algorithms that exhibit some of these promises. To improve our…

Machine Learning · Computer Science 2022-03-08 Joery A. de Vries , Thomas M. Moerland , Aske Plaat

The difference-of-convex algorithm (DCA) is a well-established nonlinear programming technique that solves successive convex optimization problems. These sub-problems are obtained from the difference-of-convex~(DC) decompositions of the…

Optimization and Control · Mathematics 2026-02-20 Hadi Abbaszadehpeivasti , Etienne de Klerk , Adrien Taylor

Current reinforcement learning algorithms train an agent using forward-generated trajectories, which provide little guidance so that the agent can explore as much as possible. While realizing the value of reinforcement learning results from…

Artificial Intelligence · Computer Science 2023-09-06 KyungMin Ko

How do we formalize the challenge of credit assignment in reinforcement learning? Common intuition would draw attention to reward sparsity as a key contributor to difficult credit assignment and traditional heuristics would look to temporal…

Machine Learning · Computer Science 2021-03-11 Dilip Arumugam , Peter Henderson , Pierre-Luc Bacon

Sparse reward problems are one of the biggest challenges in Reinforcement Learning. Goal-directed tasks are one such sparse reward problems where a reward signal is received only when the goal is reached. One promising way to train an agent…

Machine Learning · Computer Science 2018-11-06 Ameet Deshpande , Srikanth Sarma , Ashutosh Jha , Balaraman Ravindran

Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs), yet underlying mechanisms driving this success remain largely opaque. Our analysis reveals that puzzling…

Artificial Intelligence · Computer Science 2025-09-30 Haozhe Wang , Qixin Xu , Che Liu , Junhong Wu , Fangzhen Lin , Wenhu Chen

Computer vision systems that are deployed in safety-critical applications need to quantify their output uncertainty. We study regression from images to parameter values and here it is common to detect uncertainty by predicting probability…

Machine Learning · Computer Science 2024-06-24 Ziliang Xiong , Arvi Jonnarth , Abdelrahman Eldesokey , Joakim Johnander , Bastian Wandt , Per-Erik Forssen

Policy gradient methods are appealing in deep reinforcement learning but suffer from high variance of gradient estimate. To reduce the variance, the state value function is applied commonly. However, the effect of the state value function…

Machine Learning · Computer Science 2021-08-06 Jiaming Guo , Rui Zhang , Xishan Zhang , Shaohui Peng , Qi Yi , Zidong Du , Xing Hu , Qi Guo , Yunji Chen

The predominant approach in reinforcement learning is to assign credit to actions based on the expected return. However, we show that the return may depend on the policy in a way which could lead to excessive variance in value estimation…

Machine Learning · Computer Science 2023-02-07 Hsiao-Ru Pan , Nico Gürtler , Alexander Neitz , Bernhard Schölkopf

This work studies the dynamic risk management of the risk-neutral value of the potential credit losses on a portfolio of derivatives. Sensitivities-based hedging of such liability is sub-optimal because of bid-ask costs, pricing models…

Computational Finance · Quantitative Finance 2023-12-22 Roberto Daluiso , Marco Pinciroli , Michele Trapletti , Edoardo Vittori

Present incremental learning methods are limited in the ability to achieve reliable credit assignment over a large number time steps (or events). However, this situation is typical for cases where the dynamical system to be controlled…

Neural and Evolutionary Computing · Computer Science 2015-12-10 John W. Jameson

The Credit Assignment Problem (CAP) refers to the longstanding challenge of Reinforcement Learning (RL) agents to associate actions with their long-term consequences. Solving the CAP is a crucial step towards the successful deployment of RL…

Machine Learning · Computer Science 2024-07-08 Eduardo Pignatelli , Johan Ferret , Matthieu Geist , Thomas Mesnard , Hado van Hasselt , Olivier Pietquin , Laura Toni

Variational inference lies at the core of many state-of-the-art algorithms. To improve the approximation of the posterior beyond parametric families, it was proposed to include MCMC steps into the variational lower bound. In this work we…

Machine Learning · Statistics 2016-09-28 Christopher Wolf , Maximilian Karl , Patrick van der Smagt

Large Language Model (LLM) agents often face significant credit assignment challenges in long-horizon, multi-step tasks due to sparse rewards. Existing value-free methods, such as Group Relative Policy Optimization (GRPO), encounter two…

Machine Learning · Computer Science 2026-03-11 Hui-Ze Tan , Xiao-Wen Yang , Hao Chen , Jie-Jing Shao , Yi Wen , Yuteng Shen , Weihong Luo , Xiku Du , Lan-Zhe Guo , Yu-Feng Li