English
Related papers

Related papers: Softmax Q-Distribution Estimation for Structured P…

200 papers

This paper introduces an approach to Reinforcement Learning Algorithm by comparing their immediate rewards using a variation of Q-Learning algorithm. Unlike the conventional Q-Learning, the proposed algorithm compares current reward with…

Machine Learning · Computer Science 2010-09-15 Punit Pandey , Deepshikha Pandey , Shishir Kumar

This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show that a potential-based reward shaping scheme is able to…

Machine Learning · Computer Science 2019-07-23 Baicen Xiao , Bhaskar Ramasubramanian , Andrew Clark , Hannaneh Hajishirzi , Linda Bushnell , Radha Poovendran

Reward design is a fundamental problem in reinforcement learning (RL). A misspecified or poorly designed reward can result in low sample efficiency and undesired behaviors. In this paper, we propose the idea of programmatic reward design,…

Machine Learning · Computer Science 2022-01-10 Weichao Zhou , Wenchao Li

Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in logical reasoning tasks, yet whether large language model (LLM) alignment requires fundamentally different approaches remains unclear. Given the…

Artificial Intelligence · Computer Science 2026-03-12 Zhaowei Zhang , Xiaohan Liu , Xuekai Zhu , Junchao Huang , Ceyao Zhang , Zhiyuan Feng , Yaodong Yang , Xiaoyuan Yi , Xing Xie

With an eye towards human-centered automation, we contribute to the development of a systematic means to infer features of human decision-making from behavioral data. Motivated by the common use of softmax selection in models of human…

Optimization and Control · Mathematics 2015-09-01 Paul Reverdy , Naomi E. Leonard

Q-shaping is an extension of Q-value initialization and serves as an alternative to reward shaping for incorporating domain knowledge to accelerate agent training, thereby improving sample efficiency by directly shaping Q-values. This…

Artificial Intelligence · Computer Science 2024-10-03 Xiefeng Wu

Dynamic decision-making under distributional shifts is of fundamental interest in theory and applications of reinforcement learning: The distribution of the environment in which the data is collected can differ from that of the environment…

Machine Learning · Computer Science 2024-09-05 Shengbo Wang , Nian Si , Jose Blanchet , Zhengyuan Zhou

Recent works on large language models (LLMs) have successfully demonstrated the emergence of reasoning capabilities via reinforcement learning (RL). Although recent efforts leverage group relative policy optimization (GRPO) for MLLMs…

Computation and Language · Computer Science 2025-06-18 Shilin Xu , Yanwei Li , Rui Yang , Tao Zhang , Yueyi Sun , Wei Chow , Linfeng Li , Hang Song , Qi Xu , Yunhai Tong , Xiangtai Li , Hao Fei

Despite many algorithmic advances, our theoretical understanding of practical distributional reinforcement learning methods remains limited. One exception is Rowland et al. (2018)'s analysis of the C51 algorithm in terms of the Cram\'er…

Machine Learning · Computer Science 2019-02-11 Marc G. Bellemare , Nicolas Le Roux , Pablo Samuel Castro , Subhodeep Moitra

Learning to imitate expert behavior from demonstrations can be challenging, especially in environments with high-dimensional, continuous observations and unknown dynamics. Supervised learning methods based on behavioral cloning (BC) suffer…

Machine Learning · Computer Science 2019-09-27 Siddharth Reddy , Anca D. Dragan , Sergey Levine

Reward-free reinforcement learning (RL) is a framework which is suitable for both the batch RL setting and the setting where there are many reward functions of interest. During the exploration phase, an agent collects samples without using…

Machine Learning · Computer Science 2020-06-22 Ruosong Wang , Simon S. Du , Lin F. Yang , Ruslan Salakhutdinov

Sampling algorithms drive probabilistic machine learning, and recent years have seen an explosion in the diversity of tools for this task. However, the increasing sophistication of sampling algorithms is correlated with an increase in the…

Computation · Statistics 2025-07-02 Congye Wang , Matthew A. Fisher , Heishiro Kanagawa , Wilson Chen , Chris. J. Oates

Despite the fact that deep reinforcement learning (RL) has surpassed human-level performances in various tasks, it still has several fundamental challenges. First, most RL methods require intensive data from the exploration of the…

Machine Learning · Computer Science 2021-07-06 Zhe Xu , Bo Wu , Aditya Ojha , Daniel Neider , Ufuk Topcu

Although distributional reinforcement learning (DRL) has been widely examined in the past few years, very few studies investigate the validity of the obtained Q-function estimator in the distributional setting. To fully understand how the…

Machine Learning · Computer Science 2023-08-01 Qi Kuang , Zhoufan Zhu , Liwen Zhang , Fan Zhou

Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between {entropy collapse} and {entropy explosion}. We trace both hazards to the mean baseline used in value-free RL (e.g., GRPO…

Machine Learning · Computer Science 2026-03-03 Junkang Wu , Kexin Huang , Jiancan Wu , An Zhang , Xiang Wang , Xiangnan He

In offline reinforcement learning, in-sample learning methods have been widely used to prevent performance degradation caused by evaluating out-of-distribution actions from the dataset. Extreme Q-learning (XQL) employs a loss function based…

Machine Learning · Computer Science 2025-02-12 Motoki Omura , Takayuki Osa , Yusuke Mukuta , Tatsuya Harada

Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard…

Optimization and Control · Mathematics 2024-03-26 Zifan Wang , Yulong Gao , Siyi Wang , Michael M. Zavlanos , Alessandro Abate , Karl H. Johansson

Current reinforcement learning objectives for large-model reasoning primarily focus on maximizing expected rewards. This paradigm can lead to overfitting to dominant reward signals, while neglecting alternative yet valid reasoning…

Machine Learning · Computer Science 2026-02-24 Wendi Li , Sharon Li

Multi-task representation learning (MTRL) is an approach that learns shared latent representations across related tasks, facilitating collaborative learning that improves the overall learning efficiency. This paper studies MTRL for…

Machine Learning · Computer Science 2026-04-07 Yaoze Guo , Shana Moothedath

This work handles the inverse reinforcement learning (IRL) problem where only a small number of demonstrations are available from a demonstrator for each high-dimensional task, insufficient to estimate an accurate reward function. Observing…

Artificial Intelligence · Computer Science 2017-10-16 Kun Li , Joel W. Burdick