English
Related papers

Related papers: IDQL: Implicit Q-Learning as an Actor-Critic Metho…

200 papers

Large language model-based agents make mistakes, yet critique can often guide the same model toward correct behavior. However, when critique is removed, the model may fail again on the same query, indicating that it has not internalized the…

Artificial Intelligence · Computer Science 2026-05-18 Jianbo Lin , Xiaomin Yu , Yi Xin , Yifu Guo , Zhuosong Jiang , Zhongqi Yue , Weishi Wang , Heqing Zou , Chengwei Qin , Hui Xiong

In this paper, two Q-learning (QL) methods are proposed and their convergence theories are established for addressing the model-free optimal control problem of general nonlinear continuous-time systems. By introducing the Q-function for…

Systems and Control · Computer Science 2014-10-14 Biao Luo , Derong Liu , Tingwen Huang

Actor-critic methods constitute a central paradigm in reinforcement learning (RL), coupling policy evaluation with policy improvement. While effective across many domains, these methods rely on separate actor and critic networks, which…

Machine Learning · Computer Science 2025-09-26 Donghyeon Ki , Hee-Jun Ahn , Kyungyoon Kim , Byung-Jun Lee

Diffusion models typically employ static or heuristic classifier-free guidance (CFG) schedules, which often fail to adapt across timesteps and noise conditions. In this work, we introduce a quantum reinforcement learning (QRL) controller…

Quantum Physics · Physics 2025-09-18 Chi-Sheng Chen , En-Jui Kuo

Energy-based policies offer a flexible framework for modeling complex, multimodal behaviors in reinforcement learning (RL). In maximum entropy RL, the optimal policy is a Boltzmann distribution derived from the soft Q-function, but direct…

Machine Learning · Computer Science 2025-09-09 Vineet Jain , Tara Akhound-Sadegh , Siamak Ravanbakhsh

Integrating human expertise with machine learning is crucial for applications demanding high accuracy and safety, such as autonomous driving. This study introduces Interactive Double Deep Q-network (iDDQN), a Human-in-the-Loop (HITL)…

Machine Learning · Computer Science 2026-03-10 Alkis Sygkounas , Ioannis Athanasiadis , Andreas Persson , Michael Felsberg , Amy Loutfi

While a number of existing approaches for building foundation model agents rely on prompting or fine-tuning with human demonstrations, it is not sufficient in dynamic environments (e.g., mobile device control). On-policy reinforcement…

Machine Learning · Computer Science 2025-02-25 Hao Bai , Yifei Zhou , Li Erran Li , Sergey Levine , Aviral Kumar

Online interactions with the environment to collect data samples for training a Reinforcement Learning (RL) agent is not always feasible due to economic and safety concerns. The goal of Offline Reinforcement Learning is to address this…

Machine Learning · Computer Science 2021-10-05 Chi Zhang , Sanmukh Rao Kuppannagari , Viktor K Prasanna

This paper presents the first actor-critic algorithm for off-policy reinforcement learning. Our algorithm is online and incremental, and its per-time-step complexity scales linearly with the number of learned weights. Previous work on…

Machine Learning · Computer Science 2015-03-20 Thomas Degris , Martha White , Richard S. Sutton

Recent methods for imitation learning directly learn a $Q$-function using an implicit reward formulation rather than an explicit reward function. However, these methods generally require implicit reward regularization to improve stability…

Machine Learning · Computer Science 2023-03-02 Firas Al-Hafez , Davide Tateo , Oleg Arenz , Guoping Zhao , Jan Peters

Soft policies in reinforcement learning define policies as Boltzmann distributions over state-action value functions, providing a principled mechanism for balancing exploration and exploitation. However, realizing such soft policies in…

Machine Learning · Computer Science 2026-02-10 Donghyeon Ki , Hee-Jun Ahn , Kyungyoon Kim , Byung-Jun Lee

This paper concerns imitation learning (IL) (i.e, the problem of learning to mimic expert behaviors from demonstrations) in cooperative multi-agent systems. The learning problem under consideration poses several challenges, characterized by…

Machine Learning · Computer Science 2023-10-11 The Viet Bui , Tien Mai , Thanh Hong Nguyen

Consider learning an imitation policy on the basis of demonstrated behavior from multiple environments, with an eye towards deployment in an unseen environment. Since the observable features from each setting may be different, directly…

Machine Learning · Statistics 2023-11-06 Ioana Bica , Daniel Jarrett , Mihaela van der Schaar

Offline Reinforcement Learning (RL), which operates solely on static datasets without further interactions with the environment, provides an appealing alternative to learning a safe and promising control policy. The prevailing methods…

Machine Learning · Computer Science 2025-03-18 Kun Wu , Yinuo Zhao , Zhiyuan Xu , Zhengping Che , Chengxiang Yin , Chi Harold Liu , Feiferi Feng , Jian Tang

In recent years, $Q$-learning has become indispensable for model-free reinforcement learning (MFRL). However, it suffers from well-known problems such as under- and overestimation bias of the value, which may adversely affect the policy…

Machine Learning · Computer Science 2021-02-09 Youngmin Oh , Jinwoo Shin , Eunho Yang , Sung Ju Hwang

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

We propose Tabular Q-Learning (TabQL), a reinforcement learning framework that replaces the conventional parametric Q-network in Deep Q-Learning (DQN) with a tabular foundation model endowed with in-context learning capabilities. The key…

Machine Learning · Computer Science 2026-05-20 Qisai Liu , Zhanhong Jiang , Timilehin Ayanlade , Ashutosh Kumar Nirala , Yang Li , Aditya Balu , Soumik Sarkar

The vast majority of Reinforcement Learning methods is largely impacted by the computation effort and data requirements needed to obtain effective estimates of action-value functions, which in turn determine the quality of the overall…

Machine Learning · Computer Science 2025-04-04 Théo Vincent , Daniel Palenicek , Boris Belousov , Jan Peters , Carlo D'Eramo

Humans have the ability to reuse previously learned policies to solve new tasks quickly, and reinforcement learning (RL) agents can do the same by transferring knowledge from source policies to a related target task. Transfer RL methods can…

Machine Learning · Computer Science 2023-08-16 Siyuan Li , Hao Li , Jin Zhang , Zhen Wang , Peng Liu , Chongjie Zhang

Imitation learning traditionally requires complete state-action demonstrations from optimal or near-optimal experts. These requirements severely limit practical applicability, as many real-world scenarios provide only state observations…

Machine Learning · Computer Science 2025-11-06 Iason Chrysomallis , Georgios Chalkiadakis