English
Related papers

Related papers: CPG-ACTOR: Reinforcement Learning for Central Patt…

200 papers

During the training of a reinforcement learning (RL) agent, the distribution of training data is non-stationary as the agent's behavior changes over time. Therefore, there is a risk that the agent is overspecialized to a particular…

Machine Learning · Computer Science 2022-07-12 Qiang He , Huangyuan Su , Chen Gong , Xinwen Hou

This paper presents a bio-inspired central pattern generator (CPG)-type architecture for learning optimal maneuvering control of periodic locomotory gaits. The architecture is presented here with the aid of a snake robot model problem…

Systems and Control · Electrical Eng. & Systems 2019-10-08 Tixian Wang , Amirhossein Taghvaei , Prashant G. Mehta

Spring-based actuators in legged locomotion provide energy-efficiency and improved performance, but increase the difficulty of controller design. While previous work has focused on extensive modeling and simulation to find optimal…

Robotics · Computer Science 2023-08-22 Antonin Raffin , Daniel Seidel , Jens Kober , Alin Albu-Schäffer , João Silvério , Freek Stulp

This paper describes an approach for attractor selection (or multi-stability control) in nonlinear dynamical systems with constrained actuation. Attractor selection is obtained using two different deep reinforcement learning methods: 1) the…

Systems and Control · Electrical Eng. & Systems 2020-06-02 Xue-She Wang , James D. Turner , Brian P. Mann

Generalizability and stability are two key objectives for operating reinforcement learning (RL) agents in the real world. Designing RL algorithms that optimize these objectives can be a costly and painstaking process. This paper presents…

Machine Learning · Computer Science 2023-04-26 Juan Jose Garau-Luis , Yingjie Miao , John D. Co-Reyes , Aaron Parisi , Jie Tan , Esteban Real , Aleksandra Faust

We propose a general and model-free approach for Reinforcement Learning (RL) on real robotics with sparse rewards. We build upon the Deep Deterministic Policy Gradient (DDPG) algorithm to use demonstrations. Both demonstrations and actual…

In this paper, we present a model-free learning-based control scheme for the soft snake robot to improve its contact-aware locomotion performance in a cluttered environment. The control scheme includes two cooperative controllers: A…

Robotics · Computer Science 2021-05-12 Xuan Liu , Cagdas Onal , Jie Fu

All vertebrates are capable of performing various types of physical activity. Locomotor patterns are created by the cyclical coordinated work of the skeletal muscles. The organization of such a system in living organisms is responsible for…

Neurons and Cognition · Quantitative Biology 2021-12-15 A. I. Zharinov , Y. A. Tsybina , S. Y. Gordleeva

Designing an effective communication mechanism among agents in reinforcement learning has been a challenging task, especially for real-world applications. The number of agents can grow or an environment sometimes needs to interact with a…

Machine Learning · Computer Science 2022-02-01 Wei-Cheng Tseng , Wei Wei , Da-Cheng Juan , Min Sun

Pretraining with expert demonstrations have been found useful in speeding up the training process of deep reinforcement learning algorithms since less online simulation data is required. Some people use supervised learning to speed up the…

Artificial Intelligence · Computer Science 2018-02-12 Xiaoqin Zhang , Huimin Ma

Recently reinforcement learning (RL) has emerged as a promising approach for quadrupedal locomotion, which can save the manual effort in conventional approaches such as designing skill-specific controllers. However, due to the complex…

Robotics · Computer Science 2021-09-17 Haojie Shi , Bo Zhou , Hongsheng Zeng , Fan Wang , Yueqiang Dong , Jiangyong Li , Kang Wang , Hao Tian , Max Q. -H. Meng

Large Language Models (LLMs) often struggle when prompted to generate content under specific constraints. However, in such cases it is often easy to check whether these constraints are satisfied or violated. Recent works have shown that…

Computation and Language · Computer Science 2024-11-07 Liat Bezalel , Eyal Orgad , Amir Globerson

Model Predictive Control (MPC) provides interpretable, tunable locomotion controllers grounded in physical models, but its robustness depends on frequent replanning and is limited by model mismatch and real-time computational constraints.…

Robotics · Computer Science 2025-10-15 Se Hwan Jeon , Ho Jae Lee , Seungwoo Hong , Sangbae Kim

Actor-critic (AC) methods are widely used in reinforcement learning (RL) and benefit from the flexibility of using any policy gradient method as the actor and value-based method as the critic. The critic is usually trained by minimizing the…

Machine Learning · Computer Science 2023-11-01 Sharan Vaswani , Amirreza Kazemi , Reza Babanezhad , Nicolas Le Roux

Reinforcement Learning (RL) techniques have drawn great attention in many challenging tasks, but their performance deteriorates dramatically when applied to real-world problems. Various methods, such as domain randomization, have been…

Machine Learning · Computer Science 2022-08-05 Wangyang Yue , Yuan Zhou , Xiaochuan Zhang , Yuchen Hua , Zhiyuan Wang , Guang Kou

Deep reinforcement learning (DRL) has emerged as an innovative solution for controlling legged robots in challenging environments using minimalist architectures. Traditional control methods for legged robots, such as inverse dynamics,…

Robotics · Computer Science 2024-12-13 Mincheol Kim , Nahyun Kwon , Jung-Yup Kim

Learning locomotion skills is a challenging problem. To generate realistic and smooth locomotion, existing methods use motion capture, finite state machines or morphology-specific knowledge to guide the motion generation algorithms. Deep…

Machine Learning · Computer Science 2018-05-15 Wenhao Yu , Greg Turk , C. Karen Liu

Central pattern generators (CPGs) appear to have evolved multiple times throughout the animal kingdom, indicating that their design imparts a significant evolutionary advantage. Insight into how this design is achieved is hindered by the…

Biological Physics · Physics 2018-09-05 Eve Armstrong

We propose a novel hierarchical reinforcement learning framework for quadruped locomotion over challenging terrain. Our approach incorporates a two-layer hierarchy in which a high-level policy (HLP) selects optimal goals for a low-level…

Robotics · Computer Science 2025-06-26 Jeremiah Coholich , Muhammad Ali Murtaza , Seth Hutchinson , Zsolt Kira

Reinforcement learning (RL) agents typically optimize their policies by performing expensive backward passes to update their network parameters. However, some agents can solve new tasks without updating any parameters by simply conditioning…

Machine Learning · Computer Science 2025-02-13 Amir Moeini , Jiuqi Wang , Jacob Beck , Ethan Blaser , Shimon Whiteson , Rohan Chandra , Shangtong Zhang