English
Related papers

Related papers: Composite Q-learning: Multi-scale Q-function Decom…

200 papers

Deep reinforcement learning for high dimensional, hierarchical control tasks usually requires the use of complex neural networks as functional approximators, which can lead to inefficiency, instability and even divergence in the training…

Machine Learning · Computer Science 2019-11-26 Yuguang Yang

We present a novel definition of the reinforcement learning state, actions and reward function that allows a deep Q-network (DQN) to learn to control an optimization hyperparameter. Using Q-learning with experience replay, we train two DQNs…

Optimization and Control · Mathematics 2016-06-21 Samantha Hansen

This paper presents a hierarchical path-planning and control framework that combines a high-level Deep Q-Network (DQN) for discrete sub-goal selection with a low-level Twin Delayed Deep Deterministic Policy Gradient (TD3) controller for…

Robotics · Computer Science 2025-10-31 Xiaoyi He , Danggui Chen , Zhenshuo Zhang , Zimeng Bai

In temporal difference (TD) learning, off-policy sampling is known to be more practical than on-policy sampling, and by decoupling learning from data collection, it enables data reuse. It is known that policy evaluation (including…

Machine Learning · Computer Science 2021-06-25 Zaiwei Chen , Siva Theja Maguluri , Sanjay Shakkottai , Karthikeyan Shanmugam

We present a novel $l_1$ regularized off-policy convergent TD-learning method (termed RO-TD), which is able to learn sparse representations of value functions with low computational complexity. The algorithmic framework underlying RO-TD…

Machine Learning · Computer Science 2020-06-11 Bo Liu , Sridhar Mahadevan , Ji Liu

Temporal difference (TD) methods constitute a class of methods for learning predictions in multi-step prediction problems, parameterized by a recency factor lambda. Currently the most important application of these methods is to temporal…

Artificial Intelligence · Computer Science 2008-02-03 P. Cichosz

Off-policy reinforcement learning with eligibility traces is challenging because of the discrepancy between target policy and behavior policy. One common approach is to measure the difference between two policies in a probabilistic way,…

Machine Learning · Computer Science 2019-05-20 Longxiang Shi , Shijian Li , Longbing Cao , Long Yang , Gang Pan

One of the major challenges in Deep Reinforcement Learning for control is the need for extensive training to learn the policy. Motivated by this, we present the design of the Control-Tutored Deep Q-Networks (CT-DQN) algorithm, a Deep…

Machine Learning · Computer Science 2022-12-05 Francesco De Lellis , Marco Coraggio , Giovanni Russo , Mirco Musolesi , Mario di Bernardo

In this paper, we consider model-free federated reinforcement learning for tabular episodic Markov decision processes. Under the coordination of a central server, multiple agents collaboratively explore the environment and learn an optimal…

Machine Learning · Statistics 2025-03-11 Zhong Zheng , Haochen Zhang , Lingzhou Xue

Offline reinforcement learning (offline RL), which aims to find an optimal policy from a previously collected static dataset, bears algorithmic difficulties due to function approximation errors from out-of-distribution (OOD) data points. To…

Machine Learning · Computer Science 2021-10-06 Gaon An , Seungyong Moon , Jang-Hyun Kim , Hyun Oh Song

This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning for task-completion…

Computation and Language · Computer Science 2018-09-07 Shang-Yu Su , Xiujun Li , Jianfeng Gao , Jingjing Liu , Yun-Nung Chen

In experimenting with off-policy temporal difference (TD) methods in hierarchical reinforcement learning (HRL) systems, we have observed unwanted on-policy learning under reproducible conditions. Here we present modifications to several TD…

Machine Learning · Computer Science 2015-03-19 Mitchell Keith Bloch

Q-functions are widely used in discrete-time learning and control to model future costs arising from a given control policy, when the initial state and input are given. Although some of their properties are understood, Q-functions…

Optimization and Control · Mathematics 2019-02-21 Joseph Warrington

Medical treatments often involve a sequence of decisions, each informed by previous outcomes. This process closely aligns with reinforcement learning (RL), a framework for optimizing sequential decisions to maximize cumulative rewards under…

Machine Learning · Computer Science 2024-10-15 Ali Shirali , Alexander Schubert , Ahmed Alaa

Synthesizing planning and control policies in robotics is a fundamental task, further complicated by factors such as complex logic specifications and high-dimensional robot dynamics. This paper presents a novel reinforcement learning…

Robotics · Computer Science 2023-10-03 Zikang Xiong , Daniel Lawson , Joe Eappen , Ahmed H. Qureshi , Suresh Jagannathan

Off-policy reinforcement learning of pretrained flow policies remains challenging due to the instability of optimization arising from the multi-step sampling process. Recently, Q-learning with Adjoint Matching (QAM) addressed this issue by…

Machine Learning · Computer Science 2026-05-27 Yonghoon Dong , Kyungmin Lee , Changyeon Kim , Jaehyuk Kim , Jinwoo Shin

Offline-to-online reinforcement learning with action chunking eliminates multi-step off-policy bias and enables temporally coherent exploration, but all existing methods use a fixed chunk size across every state. This is suboptimal: near…

Machine Learning · Computer Science 2026-05-08 Nandiraju Gireesh , Yuanliang Ju , He Wang

Off-policy learning allows us to learn about possible policies of behavior from experience generated by a different behavior policy. Temporal difference (TD) learning algorithms can become unstable when combined with function approximation…

Machine Learning · Computer Science 2021-06-23 Ray Jiang , Tom Zahavy , Zhongwen Xu , Adam White , Matteo Hessel , Charles Blundell , Hado van Hasselt

We investigate the explainability of Reinforcement Learning (RL) policies from a temporal perspective, focusing on the sequence of future outcomes associated with individual actions. In RL, value functions compress information about rewards…

Machine Learning · Computer Science 2025-01-08 Franco Ruggeri , Alessio Russo , Rafia Inam , Karl Henrik Johansson

Previous work in hierarchical reinforcement learning has faced a dilemma: either ignore the values of different possible exit states from a subroutine, thereby risking suboptimal behavior, or represent those values explicitly thereby…

Machine Learning · Computer Science 2012-07-02 Bhaskara Marthi , Stuart Russell , David Andre