English
Related papers

Related papers: Langevin Soft Actor-Critic: Efficient Exploration …

200 papers

Actor-critic methods solve reinforcement learning problems by updating a parameterized policy known as an actor in a direction that increases an estimate of the expected return known as a critic. However, existing actor-critic methods only…

Machine Learning · Statistics 2018-02-23 Voot Tangkaratt , Abbas Abdolmaleki , Masashi Sugiyama

ATARI is a suite of video games used by reinforcement learning (RL) researchers to test the effectiveness of the learning algorithm. Receiving only the raw pixels and the game score, the agent learns to develop sophisticated strategies,…

Machine Learning · Computer Science 2024-07-17 Le Zhang , Yong Gu , Xin Zhao , Yanshuo Zhang , Shu Zhao , Yifei Jin , Xinxin Wu

The deployment of robots in uncontrolled environments requires them to operate robustly under previously unseen scenarios, like irregular terrain and wind conditions. Unfortunately, while rigorous safety frameworks from robust optimal…

Machine Learning · Computer Science 2024-06-11 Kai-Chieh Hsu , Duy Phuong Nguyen , Jaime Fernández Fisac

Off-policy actor-critic methods in reinforcement learning train a critic with temporal-difference updates and use it as a learning signal for the policy (actor). This design typically achieves higher sample efficiency than purely on-policy…

Machine Learning · Computer Science 2026-01-05 Uğurcan Özalp

Actor-critic (AC) algorithms are known for their efficacy and high performance in solving reinforcement learning problems, but they also suffer from low sampling efficiency. An AC based policy optimization process is iterative and needs to…

Machine Learning · Computer Science 2021-12-02 Chayan Banerjee , Zhiyong Chen , Nasimul Noman , Mohsen Zamani

Learning from data of past tasks can substantially improve the accuracy of mechatronic systems. Often, for fast and safe learning a model of the system is required. The aim of this paper is to develop a model-free approach for fast and safe…

Systems and Control · Electrical Eng. & Systems 2020-07-06 Maurice Poot , Jim Portegies , Tom Oomen

Reinforcement learning (RL) is a core approach for robot control when expert demonstrations are unavailable. On-policy methods such as Proximal Policy Optimization (PPO) are widely used for their stability, but their reliance on narrowly…

The effectiveness of credit assignment in reinforcement learning (RL) when dealing with high-dimensional data is influenced by the success of representation learning via deep neural networks, and has implications for the sample efficiency…

Machine Learning · Computer Science 2025-02-03 Burcu Küçükoğlu , Sander Dalm , Marcel van Gerven

The Intelligent decision of the unmanned combat aerial vehicle (UCAV) has long been a challenging problem. The conventional search method can hardly satisfy the real-time demand during high dynamics air combat scenarios. The reinforcement…

Machine Learning · Computer Science 2021-12-03 Yiwen Zhu , Zhou Fang , Yuan Zheng , Wenya Wei

The oscillating performance of off-policy learning and persisting errors in the actor-critic (AC) setting call for algorithms that can conservatively learn to suit the stability-critical applications better. In this paper, we propose a…

Machine Learning · Computer Science 2021-10-06 Lingwei Zhu , Toshinori Kitamura , Takamitsu Matsubara

We propose a new algorithm, Mean Actor-Critic (MAC), for discrete-action continuous-state reinforcement learning. MAC is a policy gradient algorithm that uses the agent's explicit representation of all action values to estimate the gradient…

We introduce a sampling perspective to tackle the challenging task of training robust Reinforcement Learning (RL) agents. Leveraging the powerful Stochastic Gradient Langevin Dynamics, we present a novel, scalable two-player RL algorithm,…

Machine Learning · Computer Science 2020-11-09 Parameswaran Kamalaruban , Yu-Ting Huang , Ya-Ping Hsieh , Paul Rolland , Cheng Shi , Volkan Cevher

To harness the full potential of beyond 5G (B5G) communication systems, zero-touch network slicing (NS) is viewed as a promising fully-automated management and orchestration (MANO) system. This paper proposes a novel knowledge plane…

Networking and Internet Architecture · Computer Science 2022-01-25 Farhad Rezazadeh , Hatim Chergui , Loizos Christofi , Christos Verikoukis

The exploration mechanism used by a Deep Reinforcement Learning (RL) agent plays a key role in determining its sample efficiency. Thus, improving over random exploration is crucial to solve long-horizon tasks with sparse rewards. We propose…

Machine Learning · Computer Science 2019-12-17 Andrey Kurenkov , Ajay Mandlekar , Roberto Martin-Martin , Silvio Savarese , Animesh Garg

Constrained Reinforcement Learning (RL) has emerged as a significant research area within RL, where integrating constraints with rewards is crucial for enhancing safety and performance across diverse control tasks. In the context of heating…

Machine Learning · Computer Science 2024-10-01 Baohe Zhang , Lilli Frison , Thomas Brox , Joschka Bödecker

Deep reinforcement learning methods have shown great performance on many challenging cooperative multi-agent tasks. Two main promising research directions are multi-agent value function decomposition and multi-agent policy gradients. In…

Artificial Intelligence · Computer Science 2021-05-11 Yuan Pu , Shaochen Wang , Rui Yang , Xin Yao , Bin Li

Ensuring the safe exploration of reinforcement learning (RL) agents is critical for deployment in real-world systems. Yet existing approaches struggle to strike the right balance: methods that tightly enforce safety often cripple task…

Machine Learning · Computer Science 2026-02-19 Daniel Bethell , Simos Gerasimou , Radu Calinescu , Calum Imrie

Multi-agent deep reinforcement learning has been applied to address a variety of complex problems with either discrete or continuous action spaces and achieved great success. However, most real-world environments cannot be described by only…

Machine Learning · Computer Science 2022-06-13 Hongzhi Hua , Kaigui Wu , Guixuan Wen

The safety constraints commonly used by existing safe reinforcement learning (RL) methods are defined only on expectation of initial states, but allow each certain state to be unsafe, which is unsatisfying for real-world safety-critical…

Machine Learning · Computer Science 2021-06-15 Haitong Ma , Yang Guan , Shegnbo Eben Li , Xiangteng Zhang , Sifa Zheng , Jianyu Chen

Proximal Policy Optimization (PPO) has become the de facto standard for training legged robots, thanks to its robustness and scalability in massively parallel simulation environments like IsaacLab. However, its on-policy nature makes it…

Robotics · Computer Science 2026-05-26 Gianluca Sabatini , Chenhao Li , Marco Hutter