English
Related papers

Related papers: SLIM: Skill Learning with Multiple Critics

200 papers

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Computation and Language · Computer Science 2024-02-20 Meng Cao , Lei Shu , Lei Yu , Yun Zhu , Nevan Wichers , Yinxiao Liu , Lei Meng

Combining model-based and model-free learning systems has been shown to improve the sample efficiency of learning to perform complex robotic tasks. However, dual-system approaches fail to consider the reliability of the learned model when…

Machine Learning · Computer Science 2020-11-03 Muhammad Burhan Hafez , Cornelius Weber , Matthias Kerzel , Stefan Wermter

Skill-based reinforcement learning (SBRL) enables rapid adaptation in environments with sparse rewards by pretraining a skill-conditioned policy. Effective skill learning requires jointly maximizing both exploration and skill diversity.…

Machine Learning · Computer Science 2026-03-17 Geonwoo Cho , Jaemoon Lee , Jaegyun Im , Subi Lee , Jihwan Lee , Sundong Kim

Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and simulation. However, most of these formulations either get stuck…

Machine Learning · Computer Science 2019-06-11 Deepak Pathak , Dhiraj Gandhi , Abhinav Gupta

Regardless of the particular task we want them to perform in an environment, there are often shared safety constraints we want our agents to respect. For example, regardless of whether it is making a sandwich or clearing the table, a…

Machine Learning · Computer Science 2023-09-06 Konwoo Kim , Gokul Swamy , Zuxin Liu , Ding Zhao , Sanjiban Choudhury , Zhiwei Steven Wu

Despite their remarkable performance, Large Language Models (LLMs) face a critical challenge: providing feedback for tasks where human evaluation is difficult or where LLMs potentially outperform humans. In such scenarios, leveraging the…

Computation and Language · Computer Science 2025-08-05 Zhengyang Tang , Ziniu Li , Zhenyang Xiao , Tian Ding , Ruoyu Sun , Benyou Wang , Dayiheng Liu , Fei Huang , Tianyu Liu , Bowen Yu , Junyang Lin

Conventional robot social behavior generation has been limited in flexibility and autonomy, relying on predefined motions or human feedback. This study proposes CRISP (Critique-and-Replan for Interactive Social Presence), an autonomous…

Robotics · Computer Science 2026-03-23 Jiyu Lim , Youngwoo Yoon , Kwanghyun Park

Recent research has demonstrated the potential of reinforcement learning in effective multi-robot collaboration, particularly in social dilemmas where robots face a trade-off between self-interest and collective benefits. However,…

Robotics · Computer Science 2026-05-25 Zexin Li , Ziliang Zhang , Hyoseung Kim , Cong Liu

This paper presents a novel method for learning reward functions for robotic motions by harnessing the power of a CLIP-based model. Traditional reward function design often hinges on manual feature engineering, which can struggle to…

Robotics · Computer Science 2025-01-30 Xuzhe Dang , Stefan Edelkamp

Reinforcement learning provides a general framework for learning robotic skills while minimizing engineering effort. However, most reinforcement learning algorithms assume that a well-designed reward function is provided, and learn a single…

Robotics · Computer Science 2020-04-28 Archit Sharma , Michael Ahn , Sergey Levine , Vikash Kumar , Karol Hausman , Shixiang Gu

Mastering robotic manipulation skills through reinforcement learning (RL) typically requires the design of shaped reward functions. Recent developments in this area have demonstrated that using sparse rewards, i.e. rewarding the agent only…

Machine Learning · Computer Science 2021-11-12 Ozsel Kilinc , Giovanni Montana

Learning contact-rich, robotic manipulation skills is a challenging problem due to the high-dimensionality of the state and action space as well as uncertainty from noisy sensors and inaccurate motor control. To combat these factors and…

Robotics · Computer Science 2020-10-06 Lin Shao , Toki Migimatsu , Jeannette Bohg

Unsupervised Skill Discovery (USD) aims to autonomously learn a diverse set of skills without relying on extrinsic rewards. One of the most common USD approaches is to maximize the Mutual Information (MI) between skill latent variables and…

Machine Learning · Computer Science 2026-02-03 Seyed Mohammad Hadi Hosseini , Mahdieh Soleymani Baghshah

Learning from few demonstrations to develop policies robust to variations in robot initial positions and object poses is a problem of significant practical interest in robotics. Compared to imitation learning, which often struggles to…

Robotics · Computer Science 2025-04-30 Haowen Sun , Han Wang , Chengzhong Ma , Shaolong Zhang , Jiawei Ye , Xingyu Chen , Xuguang Lan

Unsupervised skill discovery in Reinforcement Learning aims to mimic humans' ability to autonomously discover diverse behaviors. However, existing methods are often unconstrained, making it difficult to find useful skills, especially in…

Machine Learning · Computer Science 2025-01-30 Maxence Hussonnois , Thommen George Karimpanal , Santu Rana

Automating the segregation process is a need for every sector experiencing a high volume of materials handling, repetitive and exhaustive operations, in addition to risky exposures. Learning automated pick-and-place operations can be…

Machine Learning · Computer Science 2024-04-30 Hariharan Arunachalam , Marc Hanheide , Sariah Mghames

The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it's challenging to…

Robotics · Computer Science 2024-12-19 Changxin Huang , Yanbin Chang , Junfan Lin , Junyang Liang , Runhao Zeng , Jianqiang Li

To overcome the sparse reward challenge in reinforcement learning (RL) for agents based on large language models (LLMs), we propose Mutual Information Self-Evaluation (MISE), an RL paradigm that utilizes hindsight generative self-evaluation…

Computation and Language · Computer Science 2026-04-14 Jiashu Yao , Heyan Huang , Zeming Liu , Yuhang Guo

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…

Robotics · Computer Science 2019-02-15 Tianhe Yu , Gleb Shevchuk , Dorsa Sadigh , Chelsea Finn

Skill Incremental Learning (SIL) is the process by which an embodied agent expands and refines its skill set over time by leveraging experience gained through interaction with its environment or by the integration of additional data. SIL…

Machine Learning · Computer Science 2026-01-15 Daehee Lee , Dongsu Lee , TaeYoon Kwack , Wonje Choi , Honguk Woo