English
Related papers

Related papers: STRIDE: Automating Reward Design, Deep Reinforceme…

200 papers

Realizing interactive whole-body control for multi-humanoid systems is critical for unlocking complex collaborative capabilities in shared environments. Although recent advancements have significantly enhanced the agility of individual…

The design of reward functions in reinforcement learning is a human skill that comes with experience. Unfortunately, there is not any methodology in the literature that could guide a human to design the reward function or to allow a human…

Artificial Intelligence · Computer Science 2019-01-07 Nicholas R. Clayton , Hussein Abbass

In reinforcement learning (RL), sparse rewards are a natural way to specify the task to be learned. However, most RL algorithms struggle to learn in this setting since the learning signal is mostly zeros. In contrast, humans are good at…

Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that…

Machine Learning · Computer Science 2023-11-01 Dhawal Gupta , Yash Chandak , Scott M. Jordan , Philip S. Thomas , Bruno Castro da Silva

Reinforcement learning (RL) often struggles with reward misalignment, where agents optimize given rewards but fail to exhibit the desired behaviors. This arises when the reward function incentivizes proxy behaviors misaligned with the true…

Machine Learning · Computer Science 2025-09-19 Mohammad Saif Nazir , Chayan Banerjee

The pre-train and fine-tune paradigm in machine learning has had dramatic success in a wide range of domains because the use of existing data or pre-trained models on the internet enables quick and easy learning of new tasks. We aim to…

Robotics · Computer Science 2023-10-24 Jingyun Yang , Max Sobol Mark , Brandon Vu , Archit Sharma , Jeannette Bohg , Chelsea Finn

Humanoid robots are machines built with an anthropomorphic shape. Despite decades of research into the subject, it is still challenging to tackle the robot locomotion problem from an algorithmic point of view. For example, these machines…

Robotics · Computer Science 2020-04-28 Stefano Dafarra

We are motivated by the real challenges presented in a human-robot system to develop new designs that are efficient at data level and with performance guarantees such as stability and optimality at systems level. Existing…

Systems and Control · Electrical Eng. & Systems 2021-01-19 Xiang Gao , Jennie Si , Yue Wen , Minhan Li , He , Huang

Legged locomotion is widespread in nature and has inspired the design of current robots. The controller of these legged robots is often realized as one centralized instance. However, in nature, control of movement happens in a hierarchical…

Artificial Intelligence · Computer Science 2022-10-18 W. Zai El Amri , L. Hermes , M. Schilling

Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new…

Machine Learning · Computer Science 2021-07-22 Karl Pertsch , Youngwoon Lee , Yue Wu , Joseph J. Lim

Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences…

Machine Learning · Computer Science 2026-04-06 Yiqin Yang , Hao Hu , Yihuan Mao , Jin Zhang , Chengjie Wu , Yuhua Jiang , Xu Yang , Runpeng Xie , Yi Fan , Bo Liu , Yang Gao , Bo Xu , Chongjie Zhang

Deep reinforcement learning (DRL) is a promising approach for developing legged locomotion skills. However, the iterative design process that is inevitable in practice is poorly supported by the default methodology. It is difficult to…

Robotics · Computer Science 2019-03-25 Zhaoming Xie , Patrick Clary , Jeremy Dao , Pedro Morais , Jonathan Hurst , Michiel van de Panne

The effectiveness of reinforcement learning (RL) agents in continuous control robotics tasks is mainly dependent on the design of the underlying reward function, which is highly prone to reward hacking. A misalignment between the reward…

Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance performance, the computational overhead is a critical issue. In…

Machine Learning · Computer Science 2026-03-27 Jiahao Wu , Ning Lu , Shengcai Liu , Kun Wang , Yanting Yang , Li Qing , Ke Tang

Traversing risky terrains with sparse footholds poses a significant challenge for humanoid robots, requiring precise foot placements and stable locomotion. Existing learning-based approaches often struggle on such complex terrains due to…

Robotics · Computer Science 2025-04-29 Huayi Wang , Zirui Wang , Junli Ren , Qingwei Ben , Tao Huang , Weinan Zhang , Jiangmiao Pang

Developing an automated driving system capable of navigating complex traffic environments remains a formidable challenge. Unlike rule-based or supervised learning-based methods, Deep Reinforcement Learning (DRL) based controllers eliminate…

Machine Learning · Computer Science 2025-01-28 Zhihao Zhang , Ekim Yurtsever , Keith A. Redmill

Controlling a non-statically bipedal robot is challenging due to the complex dynamics and multi-criterion optimization involved. Recent works have demonstrated the effectiveness of deep reinforcement learning (DRL) for simulation and…

Robotics · Computer Science 2021-12-23 Changxin Huang , Guangrun Wang , Zhibo Zhou , Ronghui Zhang , Liang Lin

Humans naturally swing their arms during locomotion to regulate whole-body dynamics, reduce angular momentum, and help maintain balance. Inspired by this principle, we present a limb-level multi-agent reinforcement learning (RL) framework…

Robotics · Computer Science 2025-07-08 Ho Jae Lee , Se Hwan Jeon , Sangbae Kim

Agile and adaptive maneuvers such as fall recovery, high-speed turning, and sprinting in the wild are challenging for legged systems. We propose a Curricular Hindsight Reinforcement Learning (CHRL) that learns an end-to-end tracking…

Robotics · Computer Science 2023-10-25 Sicen Li , Yiming Pang , Panju Bai , Zhaojin Liu , Jiawei Li , Shihao Hu , Liquan Wang , Gang Wang

Designing reward functions is a longstanding challenge in reinforcement learning (RL); it requires specialized knowledge or domain data, leading to high costs for development. To address this, we introduce Text2Reward, a data-free framework…

Machine Learning · Computer Science 2024-05-28 Tianbao Xie , Siheng Zhao , Chen Henry Wu , Yitao Liu , Qian Luo , Victor Zhong , Yanchao Yang , Tao Yu