English
Related papers

Related papers: Mixture-of-World Models: Scaling Multi-Task Reinfo…

200 papers

Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have significantly improved the adaptation of LLMs to downstream tasks in a resource-efficient manner. However, in multi-task scenarios, challenges such as training imbalance and the…

Computation and Language · Computer Science 2024-10-31 Xujia Wang , Haiyan Zhao , Shuo Wang , Hanqing Wang , Zhiyuan Liu

World models (WMs) represent the frontier of sample-efficient reinforcement learning, but their complexity leaves many promising improvements unrealized due to the significant expertise and effort required to identify and integrate them.…

Machine Learning · Computer Science 2026-05-12 Lior Cohen , Kaixin Wang , Bingyi Kang , Uri Gadot , Shie Mannor

Reinforcement learning has been demonstrated as a flexible and effective approach for learning a range of continuous control tasks, such as those used by robots to manipulate objects in their environment. But in robotics particularly,…

Robotics · Computer Science 2022-10-25 Tuluhan Akbulut , Max Merlin , Shane Parr , Benedict Quartey , Skye Thompson

Many real-world large-scale regression problems can be formulated as Multi-task Learning (MTL) problems with a massive number of tasks, as in retail and transportation domains. However, existing MTL methods still fail to offer both the…

Machine Learning · Computer Science 2018-11-15 Xiao He , Francesco Alesiani , Ammar Shaker

Visual deep reinforcement learning (RL) enables robots to acquire skills from visual input for unstructured tasks. However, current algorithms suffer from low sample efficiency, limiting their practical applicability. In this work, we…

Robotics · Computer Science 2025-07-08 Suning Huang , Zheyu Zhang , Tianhai Liang , Yihan Xu , Zhehao Kou , Chenhao Lu , Guowei Xu , Zhengrong Xue , Huazhe Xu

Multi-Objective Reinforcement Learning (MORL) is a generalization of traditional Reinforcement Learning (RL) that aims to optimize multiple, often conflicting objectives simultaneously rather than focusing on a single reward. This approach…

Machine Learning · Computer Science 2025-08-15 Davide Guidobene , Lorenzo Benedetti , Diego Arapovic

Multitask Reinforcement Learning (MTRL) approaches have gained increasing attention for its wide applications in many important Reinforcement Learning (RL) tasks. However, while recent advancements in MTRL theory have focused on the…

Machine Learning · Statistics 2024-03-07 Ziping Xu , Zifan Xu , Runxuan Jiang , Peter Stone , Ambuj Tewari

In recent years, Model-based Multi-Agent Reinforcement Learning (MARL) has demonstrated significant advantages over model-free methods in terms of sample efficiency by using independent environment dynamics world models for data sample…

Multiagent Systems · Computer Science 2025-01-20 Zifeng Shi , Meiqin Liu , Senlin Zhang , Ronghao Zheng , Shanling Dong , Ping Wei

Intelligent agents need to generalize from past experience to achieve goals in complex environments. World models facilitate such generalization and allow learning behaviors from imagined outcomes to increase sample-efficiency. While…

Machine Learning · Computer Science 2022-02-15 Danijar Hafner , Timothy Lillicrap , Mohammad Norouzi , Jimmy Ba

Mixture-of-Experts (MoE) models have shown remarkable capability in instruction tuning, especially when the number of tasks scales. However, previous methods simply merge all training tasks (e.g. creative writing, coding, and mathematics)…

Computation and Language · Computer Science 2024-06-18 Tong Zhu , Daize Dong , Xiaoye Qu , Jiacheng Ruan , Wenliang Chen , Yu Cheng

Multi-task learning (MTL) aims to improve generalization performance by learning multiple related tasks simultaneously. While sometimes the underlying task relationship structure is known, often the structure needs to be estimated from data…

Meta-reinforcement learning enables artificial agents to learn from related training tasks and adapt to new tasks efficiently with minimal interaction data. However, most existing research is still limited to narrow task distributions that…

Machine Learning · Computer Science 2023-05-02 Mingyang Wang , Zhenshan Bing , Xiangtong Yao , Shuai Wang , Hang Su , Chenguang Yang , Kai Huang , Alois Knoll

Model agnostic meta-learning (MAML) is a popular state-of-the-art meta-learning algorithm that provides good weight initialization of a model given a variety of learning tasks. The model initialized by provided weight can be fine-tuned to…

Machine Learning · Computer Science 2021-06-11 Thanh Nguyen , Tung Luu , Trung Pham , Sanzhar Rakhimkul , Chang D. Yoo

Conventional control, such as model-based control, is commonly utilized in autonomous driving due to its efficiency and reliability. However, real-world autonomous driving contends with a multitude of diverse traffic scenarios that are…

Robotics · Computer Science 2024-03-08 Vindula Jayawardana , Sirui Li , Cathy Wu , Yashar Farid , Kentaro Oguchi

Humans have consciousness as the ability to perceive events and objects: a mental model of the world developed from the most impoverished of visual stimuli, enabling humans to make rapid decisions and take actions. Although spatial and…

Artificial Intelligence · Computer Science 2018-11-06 Lisheng Wu , Minne Li , Jun Wang

General-purpose control demands agents that act across many tasks and embodiments, yet research on reinforcement learning (RL) for continuous control remains dominated by single-task or offline regimes, reinforcing a view that online RL…

Machine Learning · Computer Science 2025-12-03 Nicklas Hansen , Hao Su , Xiaolong Wang

Multi-task learning (MTL) is a methodology that aims to improve the general performance of estimation and prediction by sharing common information among related tasks. In the MTL, there are several assumptions for the relationships and…

Methodology · Statistics 2023-04-27 Akira Okazaki , Shuichi Kawano

While robot learning has demonstrated promising results for enabling robots to automatically acquire new skills, a critical challenge in deploying learning-based systems is scale: acquiring enough data for the robot to effectively…

Reinforcement learning with multiple, potentially conflicting objectives is pervasive in real-world applications, while this problem remains theoretically under-explored. This paper tackles the multi-objective reinforcement learning (MORL)…

Machine Learning · Computer Science 2024-05-10 Tianchen Zhou , FNU Hairi , Haibo Yang , Jia Liu , Tian Tong , Fan Yang , Michinari Momma , Yan Gao

We present a novel reinforcement learning based algorithm for multi-robot task allocation problem in warehouse environments. We formulate it as a Markov Decision Process and solve via a novel deep multi-agent reinforcement learning method…

Robotics · Computer Science 2023-02-28 Aakriti Agrawal , Amrit Singh Bedi , Dinesh Manocha