English
Related papers

Related papers: Transferable Curricula through Difficulty Conditio…

200 papers

Parameter estimation for dynamical systems remains challenging due to non-convexity and sensitivity to initial parameter guesses. Recent deep learning approaches enable accurate and fast parameter estimation but do not exploit transferable…

Systems and Control · Electrical Eng. & Systems 2026-04-08 Fabian Raisch , Timo Germann , J. Nathan Kutz , Christoph Goebel , Benjamin Tischler

For reinforcement learning (RL), it is challenging for an agent to master a task that requires a specific series of actions due to sparse rewards. To solve this problem, reverse curriculum generation (RCG) provides a reverse expansion…

Machine Learning · Computer Science 2021-08-05 Zih-Yun Chiu , Yi-Lin Tuan , Hung-yi Lee , Li-Chen Fu

Recent curriculum Reinforcement Learning (RL) has shown notable progress in solving complex tasks by proposing sequences of surrogate tasks. However, the previous approaches often face challenges when they generate curriculum goals in a…

Machine Learning · Computer Science 2023-10-27 Seungjae Lee , Daesol Cho , Jonghae Park , H. Jin Kim

Designing effective task sequences is crucial for curriculum reinforcement learning (CRL), where agents must gradually acquire skills by training on intermediate tasks. A key challenge in CRL is to identify tasks that promote exploration,…

Machine Learning · Computer Science 2025-07-08 Geonwoo Cho , Jaegyun Im , Doyoon Kim , Sundong Kim

Training Vision-Language Models (VLMs) for Graphical User Interfaces (GUI) agents via Reinforcement Learning (RL) faces critical challenges: environment-based RL requires costly interactions, while environment-free methods struggle with…

Machine Learning · Computer Science 2025-02-27 Jiani Zheng , Lu Wang , Fangkai Yang , Chaoyun Zhang , Lingrui Mei , Wenjie Yin , Qingwei Lin , Dongmei Zhang , Saravan Rajmohan , Qi Zhang

Vision-and-Language Navigation (VLN) is a task where an agent navigates in an embodied indoor environment under human instructions. Previous works ignore the distribution of sample difficulty and we argue that this potentially degrade their…

Machine Learning · Computer Science 2021-11-16 Jiwen Zhang , Zhongyu Wei , Jianqing Fan , Jiajie Peng

Curriculum learning (CL) posits that machine learning models -- similar to humans -- may learn more efficiently from data that match their current learning progress. However, CL methods are still poorly understood and, in particular for…

Machine Learning · Computer Science 2023-08-24 Lucas Weber , Jaap Jumelet , Paul Michel , Elia Bruni , Dieuwke Hupkes

Reward models trained through Reinforcement Learning from AI Feedback (RLAIF) methods frequently suffer from limited generalizability, which hinders the alignment performance of policy models. This challenge stems from various issues,…

Artificial Intelligence · Computer Science 2026-04-21 Jiaye Lin , Mengdi Li , Xufeng Zhao , Wenhao Lu , Peilin Zhao , Stefan Wermter , Di Wang

Sustainability is becoming increasingly critical in the maritime transport, encompassing both environmental and social impacts, such as Greenhouse Gas (GHG) emissions and navigational safety. Traditional vessel navigation heavily relies on…

Machine Learning · Computer Science 2026-01-19 Zhang Xiaocai , Xiao Zhe , Liang Maohan , Liu Tao , Li Haijiang , Zhang Wenbin

Unsupervised Environment Design (UED) is a paradigm for automatically generating a curriculum of training environments, enabling agents trained in these environments to develop general capabilities, i.e., achieving good zero-shot transfer…

Machine Learning · Computer Science 2024-02-16 Dexun Li , Pradeep Varakantham

Generalization in Reinforcement Learning (RL) aims to learn an agent during training that generalizes to the target environment. This paper studies RL generalization from a theoretical aspect: how much can we expect pre-training over…

Machine Learning · Computer Science 2023-06-30 Haotian Ye , Xiaoyu Chen , Liwei Wang , Simon S. Du

Designing reinforcement learning curricula for agile robots traditionally requires extensive manual tuning of reward functions, environment randomizations, and training configurations. We introduce AURA (Autonomous Upskilling with…

Robotics · Computer Science 2025-11-06 Alvin Zhu , Yusuke Tanaka , Andrew Goldberg , Dennis Hong

Learning-based approaches, particularly reinforcement learning (RL), have become widely used for developing control policies for autonomous agents, such as locomotion policies for legged robots. RL training typically maximizes a predefined…

Robotics · Computer Science 2025-04-23 Dylan Khor , Bowen Weng

This paper presents a novel and sustainable approach for improving beam selection in 5G and beyond networks using transfer learning and Reinforcement Learning (RL). Traditional RL-based beam selection models require extensive training time…

Machine Learning · Computer Science 2025-11-18 Dariush Salami , Ramin Hashemi , Parham Kazemi , Mikko A. Uusitalo

Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and code generation. A crucial factor influencing RL fine-tuning…

Artificial Intelligence · Computer Science 2025-10-31 Xiaoyin Chen , Jiarui Lu , Minsu Kim , Dinghuai Zhang , Jian Tang , Alexandre Piché , Nicolas Gontier , Yoshua Bengio , Ehsan Kamalloo

Large Language Model (LLM) agents can leverage multiple turns and tools to solve complex tasks, with prompt-based approaches achieving strong performance. This work demonstrates that Reinforcement Learning (RL) can push capabilities…

Computation and Language · Computer Science 2025-10-29 Vivek Kalyan , Martin Andrews

Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically suffer from three core difficulties: temporal credit assignment with sparse rewards, lack…

Machine Learning · Computer Science 2018-10-30 Shauharda Khadka , Kagan Tumer

Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…

Machine Learning · Computer Science 2020-05-28 Yiming Ding , Carlos Florensa , Mariano Phielipp , Pieter Abbeel

While physically-based rendering (PBR) simulates light transport that guarantees physical realism, achieving true photorealistic rendering (PRR) demands prohibitive time and labor, and still struggles to capture the intractable richness of…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jiayuan Lu , Rengan Xie , Xuancheng Jin , Zhizhen Wu , Qi Ye , Tian Xie , Hujun Bao , Rui Wang. Yuchi Huo

Parameter efficient learning methods (PERMs) have recently gained significant attention as they provide an efficient way for pre-trained language models (PLMs) to adapt to a downstream task. However, these conclusions are mostly drawn from…

Computation and Language · Computer Science 2022-10-26 Peng Xu , Mostofa Patwary , Shrimai Prabhumoye , Virginia Adams , Ryan J. Prenger , Wei Ping , Nayeon Lee , Mohammad Shoeybi , Bryan Catanzaro