Deep Deterministic Policy Gradient

Also known as DDPG

Deep Deterministic Policy Gradient (DDPG) learns continuous actions with an actor–critic: a deterministic policy is updated using gradients from a learned critic, while replay buffers and target networks support off-policy training. It is useful for control problems involving actions such as robot movements, vehicle steering, or resource allocation, where discretizing actions is impractical. Extensions include twin-delayed critics (TD3), smoothed or constrained policy gradients, domain-knowledge-guided learning, and multi-agent or continuous-time variants, tested in continuous-control benchmarks and simulated or real-world tasks. A central challenge is keeping critic estimates and action gradients reliable: overestimation and poor exploration can destabilize learning, especially with sparse rewards, hybrid actions, or changing dynamics.

Latest papers

17 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Boundary-aware Reinforcement Learning for Hypercube State Spaces via Deterministic Policy Gradient
Oct 7, 2026Lijun Bo, Yijie Huang, Chenhao LuRL Control Reinforcement Learning
School of Mathematics and Statistics, Xidian University, Xi’an, 710126, China · Department of Applied Mathematics, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China · School of Mathematical Sciences, University of Science and Technology of China, Hefei, 230026, China
Continuous-Time Reinforcement Learning for Controlled Hawkes Jump-Diffusions
Aug 19, 2026Tomasz R. Bielecki, Thibaut Mastrolia, Haoze YanStochastic Optimal Control Continuous-Time RL
Hinsdale, Illinois, USA · UC Berkeley, Department of Industrial Engineering and Operations Research, USA
Multi-Agent Off-Policy Deep Reinforcement Learning for Smart Campus Coverage
Aug 19, 2026Omar Rady, Mohamed Ayman, Ali Arafa +1Millimeter-Wave Communications Wireless Communications
Faculty of Information Engineering and Technology The German University in Cairo Cairo, Egypt
A Self-Evolving Default Action for Cooperative Tasks with Continuous Action Space
Jul 21, 2026Shuangyao HuangPolicy Gradient Credit Assignment
Xi’an Jiaotong-Liverpool University School of Internet of Things
CLaC@FinMMEval 2026 Task 3: Sentiment-Augmented Deep Reinforcement Learning for Active Trading -- An Alpha-Reward Approach
Jul 17, 2026Andrei Neagu, Eeham Khan, Leila KosseimReinforcement Learning Deep Q-Learning
Department of Computer Science and Software Engineering, Concordia University, Montréal, Canada
3D Geometric Tooth Alignment Planning via Deep Reinforcement Learning
Jul 16, 2026Yong Li, Jianwen Lou, Jiayue Ma +3Reinforcement Learning Healthcare
School of Software Technology, Zhejiang University, Hangzhou, China · State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China · Stomatology Hospital, Zhejiang University School of Medicine, Hangzhou, China
Actor-Critic Learning for Extended Mean Field Control with Deterministic Policies
Jul 13, 2026Ziheng Cheng, Xin Guo, Huyên Pham +1Policy Gradient Continuous-Time RL
University of California, Berkeley · Ecole Polytechnique, CMAP · Imperial College London
DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement Learning
Jul 2, 2026Yueming Huang, Wenhan Yao, Fen Xiao +2Backdoor Attacks Deep Deterministic Policy Gradient
Xiangtan University, Yuhu District Xiangda Road, Xiangtan, 411100, Hunan, China · Peking University, No.5, Summer Palace Road, Haidian District, Beijing, China, Beijing, 100871, Beijing, China
FlowDPG: Deterministic Policy Gradient on Flow Matching Policies for Real-World Manipulation
Jun 21, 2026Kexin Shi, Junyao Shi, Poorvi Hebbar +5Deep Deterministic Policy Gradient Policy Gradient
Skild AI · Carnegie Mellon University · University of Pennsylvania
Deterministic Policy Gradient for Learning Equilibrium in Time-Inconsistent Control Problems
Jun 10, 2026Xin Guo, Yijie Huang, Xiang YuPolicy Gradient Stochastic Optimal Control
Department of Industrial Engineering and Operations Research, University of California, Berkeley, USA. · Department of Applied Mathematics, The Hong Kong Polytechnic University, Kowloon, Hong Kong.
Path Planning Using Deep Deterministic Policy Gradient: A Reinforcement Learning Approach
Jun 5, 2026Qiang Le, Yaguang Yang, Isaac E. WeintraubConstrained Motion Planning Safe Motion Planning
Hampton University, Hampton, VA 23669, USA · Air Force Research Laboratory, Wright-Patterson AFB, OH 45433, USA
Modeling Vehicle-Type-Specific Pedestrian Crash Avoidance Behavior in Safety-Critical Interactions Using Smooth-Mamba Deep Reinforcement Learning
May 27, 2026Qingwen Pu, Kun Xie, Hong Yang +2Collision Avoidance Pedestrian Behavior Modeling
Transportation Informatics Lab, Department of Civil and Environmental Engineering, Old Dominion University, Norfolk, VA 23529, United States · Department of Electrical and Computer Engineering, Old Dominion University, Norfolk, VA, United States · Department of Transportation and Urban Infrastructure Studies, SMARTER Center, Morgan State University, 1700 E Cold Spring Ln, Baltimore, MD 21251, USA
Identifying Culprits Through Deep Deterministic Policy Gradient Deep Learning Investigation
May 14, 2026Lata B T, Savitha N JDeep Deterministic Policy Gradient
Dept. of CSE, UVCE, Bengaluru, India.
Soft Deterministic Policy Gradient with Gaussian Smoothing
May 7, 2026Hyunjun Na, Donghwan LeeRL Control Policy Gradient
School of Electrical Engineering, KAIST 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Korea
Dynamic resource matching in manufacturing using deep reinforcement learning
Mar 28, 2026Saunak Kumar Panda, Yisha Xiang, Ruiqi LiuManufacturing RL for Combinatorial Optimization
Department of Industrial Engineering, University of Houston, Houston, TX 77004, USA · Department of Mathematics and Statistics, Texas Tech University, Lubbock, TX 79409, USA
GAN-Enhanced Deep Reinforcement Learning for Semantic-Aware Resource Allocation in 6G Network Slicing
Mar 27, 2026Daniel Benniah JohnNetwork Slicing Wireless Resource Allocation
University of California, Berkeley, CA, USA
Hybrid TD3: Overestimation Bias Analysis and Stable Policy Optimization for Hybrid Action Space
Mar 1, 2026Thanh-Tuan Tran, Thanh Nguyen Canh, Nak Young Chong +1Hybrid Action Space RL Reinforcement Learning
University of Engineering and Technology, Vietnam National University, 10000, Hanoi, Vietnam. · School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, 923-1211, Ishikawa, Japan. · Department of Robotics, Hanyang University, Ansan, 15588, Gyeonggi, Korea.

Oct 7, 2026J/K move · Enter open · S save

Boundary-aware Reinforcement Learning for Hypercube State Spaces via Deterministic Policy Gradient

Lijun Bo, Yijie Huang, Chenhao Lu

School of Mathematics and Statistics, Xidian University, Xi’an, 710126, China · Department of Applied Mathematics, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China · School of Mathematical Sciences, University of Science and Technology of China, Hefei, 230026, China

RL Control Reinforcement Learning Continuous-Time RL Deep Deterministic Policy Gradient Stochastic Differential Equations

Open paper AskPDF arXiv

We develop a continuous-time deterministic policy gradient framework for reinforcement learning with reflected state dynamics, where the state process is governed by a controlled reflected stochastic differential equation on a hypercube. Under suitable regularity assumptions, we establish the connection between the value function and the Neumann Bellman equation, introduce an advantage-rate function that yields a deterministic policy gradient formula, and prove the martingale characterization theorem. Motivated by these theoretical results, we propose a continuous-time deep deterministic policy gradient algorithm for reflected stochastic systems, in which the Neumann boundary condition is imposed via either soft penalization or hard architectural constraint. We further quantify the discrepancy between the ideal continuous-time dynamics and the discretely sampled exploratory dynamics executed in practice, showing that the error decays as the time grid is refined and exploration noise vanishes. Our experiments on reservoir control problems illustrate the effectiveness of the RL framework, highlighting that boundary-aware methods substantially reduce Neumann boundary residuals and enhance learning stability.