English
Related papers

Related papers: Good Actions Succeed, Bad Actions Generalize: A Ca…

200 papers

While goal-conditioned behavior cloning (GCBC) methods can perform well on in-distribution training tasks, they do not necessarily generalize zero-shot to tasks that require conditioning on novel state-goal pairs, i.e. combinatorial…

Machine Learning · Computer Science 2026-04-21 Daniel Lawson , Adriana Hugessen , Charlotte Cloutier , Glen Berseth , Khimya Khetarpal

Aligning large language models (LLMs) on domain-specific data remains a fundamental challenge. Supervised fine-tuning (SFT) offers a straightforward way to inject domain knowledge but often degrades the model's generality. In contrast,…

Machine Learning · Computer Science 2026-02-12 Linxuan Xia , Xiaolong Yang , Yongyuan Chen , Enyue Zhao , Deng Cai , Yasheng Wang , Boxi Wu

Recently, empowered with the powerful capabilities of neural networks, reinforcement learning (RL) has successfully tackled numerous challenging tasks. However, while these models demonstrate enhanced decision-making abilities, they are…

Machine Learning · Computer Science 2025-10-09 Zhengpeng Xie , Yulong Zhang

Representation learning algorithms are designed to learn abstract features that characterize data. State representation learning (SRL) focuses on a particular kind of representation learning where learned features are in low dimension,…

Artificial Intelligence · Computer Science 2018-10-30 Timothée Lesort , Natalia Díaz-Rodríguez , Jean-François Goudou , David Filliat

Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization. Recent efforts apply meta-learning to learn a meta-learner from a set of RL tasks such that a novel but related task…

Machine Learning · Computer Science 2019-06-05 Lin Lan , Zhenguo Li , Xiaohong Guan , Pinghui Wang

The adaptation of large-scale Vision-Language Models (VLMs) through post-training reveals a pronounced generalization gap: models fine-tuned with Reinforcement Learning (RL) consistently achieve superior out-of-distribution (OOD)…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Aojun Lu , Tao Feng , Hangjie Yuan , Wei Li , Yanan Sun

Humans perceive the world through multiple senses, enabling them to create a comprehensive representation of their surroundings and to generalize information across domains. For instance, when a textual description of a scene is given,…

Artificial Intelligence · Computer Science 2025-06-05 Léopold Maytié , Benjamin Devillers , Alexandre Arnold , Rufin VanRullen

Modern RAN operate in highly dynamic and heterogeneous environments, where hand-tuned, rule-based RRM algorithms often underperform. While RL can surpass such heuristics in constrained settings, the diversity of deployments and…

Machine Learning · Computer Science 2026-01-29 Burak Demirel , Yu Wang , Cristian Tatino , Pablo Soldati

The generalization gap in reinforcement learning (RL) has been a significant obstacle that prevents the RL agent from learning general skills and adapting to varying environments. Increasing the generalization capacity of the RL systems can…

Machine Learning · Computer Science 2021-12-06 Hanping Zhang , Yuhong Guo

Many model-based reinforcement learning (RL) methods follow a similar template: fit a model to previously observed data, and then use data from that model for RL or planning. However, models that achieve better training performance (e.g.,…

Machine Learning · Computer Science 2023-02-21 Benjamin Eysenbach , Alexander Khazatsky , Sergey Levine , Ruslan Salakhutdinov

Robotic control policies learned from human demonstrations have achieved impressive results in many real-world applications. However, in scenarios where initial performance is not satisfactory, as is often the case in novel open-world…

Learning robot skills from scratch is often time-consuming, while reusing data promotes sustainability and improves sample efficiency. This study investigates policy transfer across different robotic platforms, focusing on peg-in-hole task…

Robotics · Computer Science 2026-04-09 Khalil Abuibaid , Vinit Hegiste , Nigora Gafur , Achim Wagner , Martin Ruskowski

Reinforcement learning (RL) agents need to explore their environments in order to learn optimal policies. In many environments and tasks, safety is of critical importance. The widespread use of simulators offers a number of advantages,…

Robotics · Computer Science 2024-03-01 Luka Kovač , Igor Farkaš

Vision-Language-Action (VLA) models excel in robotic manipulation but are constrained by their heavy reliance on expert demonstrations, leading to demonstration bias and limiting performance. Reinforcement learning (RL) is a vital…

Robotics · Computer Science 2025-12-02 Senyu Fei , Siyin Wang , Li Ji , Ao Li , Shiduo Zhang , Liming Liu , Jinlong Hou , Jingjing Gong , Xianzhong Zhao , Xipeng Qiu

We consider the problem of generalization in reinforcement learning where visual aspects of the observations might differ, e.g. when there are different backgrounds or change in contrast, brightness, etc. We assume that our agent has access…

Machine Learning · Computer Science 2021-02-16 Bonnie Li , Vincent François-Lavet , Thang Doan , Joelle Pineau

Despite the significant progress of deep reinforcement learning (RL) in solving sequential decision making problems, RL agents often overfit to training environments and struggle to adapt to new, unseen environments. This prevents robust…

Machine Learning · Computer Science 2020-08-04 Xingyu Lu , Kimin Lee , Pieter Abbeel , Stas Tiomkin

Real-time learning is crucial for robotic agents adapting to ever-changing, non-stationary environments. A common setup for a robotic agent is to have two different computers simultaneously: a resource-limited local computer tethered to the…

Robotics · Computer Science 2023-06-28 Yan Wang , Gautham Vasan , A. Rupam Mahmood

Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep…

Machine Learning · Computer Science 2016-09-23 Coline Devin , Abhishek Gupta , Trevor Darrell , Pieter Abbeel , Sergey Levine

Crop production management is essential for optimizing yield and minimizing a field's environmental impact to crop fields, yet it remains challenging due to the complex and stochastic processes involved. Recently, researchers have turned to…

Systems and Control · Electrical Eng. & Systems 2024-11-07 Joseph Balderas , Dong Chen , Yanbo Huang , Li Wang , Ren-Cang Li

Optimizing the fuel cycle cost through the optimization of nuclear reactor core loading patterns involves multiple objectives and constraints, leading to a vast number of candidate solutions that cannot be explicitly solved. To advance the…

Neural and Evolutionary Computing · Computer Science 2024-07-16 Paul Seurin , Koroush Shirvan