English
Related papers

Related papers: Learning From Failures: Efficient Reinforcement Le…

200 papers

Learning from human demonstrations can facilitate automation but is risky because the execution of the learned policy might lead to collisions and other failures. Adding explicit constraints to avoid unsafe states is generally not possible…

Robotics · Computer Science 2018-10-17 Jonathan Lee , Michael Laskey , Roy Fox , Ken Goldberg

Recent advances in batch (offline) reinforcement learning have shown promising results in learning from available offline data and proved offline reinforcement learning to be an essential toolkit in learning control policies in a model-free…

Machine Learning · Computer Science 2022-12-19 Ashish Kumar , Ilya Kuzovkin

Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a reward signal. We extend the residual formulation to learn…

Machine Learning · Computer Science 2021-06-16 Minttu Alakuijala , Gabriel Dulac-Arnold , Julien Mairal , Jean Ponce , Cordelia Schmid

Deep reinforcement learning for continuous control has recently achieved impressive progress. However, existing methods often suffer from primacy bias, a tendency to overfit early experiences stored in the replay buffer, which limits an RL…

Machine Learning · Computer Science 2025-07-04 Zilin Kang , Chenyuan Hu , Yu Luo , Zhecheng Yuan , Ruijie Zheng , Huazhe Xu

Reinforcement learning-based (RL-based) energy management strategy (EMS) is considered a promising solution for the energy management of electric vehicles with multiple power sources. It has been shown to outperform conventional methods in…

Artificial Intelligence · Computer Science 2022-12-20 Jincheng Hu , Yang Lin , Jihao Li , Zhuoran Hou , Dezong Zhao , Quan Zhou , Jingjing Jiang , Yuanjian Zhang

Reinforcement learning provides an appealing framework for robotic control due to its ability to learn expressive policies purely through real-world interaction. However, this requires addressing real-world constraints and avoiding…

Robotics · Computer Science 2024-05-09 Kyle Stachowicz , Sergey Levine

This work introduces a robot navigation controller that combines event cameras and other sensors with reinforcement learning to enable real-time human-centered navigation and obstacle avoidance. Unlike conventional image-based controllers,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-13 Ignacio Bugueno-Cordova , Javier Ruiz-del-Solar , Rodrigo Verschae

Street Scene Semantic Understanding (denoted as S3U) is a crucial but complex task for autonomous driving (AD) vehicles. Their inference models typically face poor generalization due to domain-shift. Federated Learning (FL) has emerged as a…

Robotics · Computer Science 2025-05-02 Wei-Bin Kou , Guangxu Zhu , Bingyang Cheng , Shuai Wang , Ming Tang , Yik-Chung Wu

Continual learning is an essential capability of human cognition, yet it poses significant challenges for current deep learning models. The primary issue is that new knowledge can interfere with previously learned information, causing the…

Machine Learning · Computer Science 2025-09-19 Eric Nuertey Coleman , Luigi Quarantiello , Samrat Mukherjee , Julio Hurtado , Vincenzo Lomonaco

The stability-plasticity dilemma is a major challenge in continual learning, as it involves balancing the conflicting objectives of maintaining performance on previous tasks while learning new tasks. In this paper, we propose the…

Machine Learning · Computer Science 2024-03-06 Haneol Kang , Dong-Wan Choi

Reinforcement Learning (RL) is an emerging approach to control many dynamical systems for which classical control approaches are not applicable or insufficient. However, the resultant policies may not generalize to variations in the…

Robotics · Computer Science 2023-11-13 Abdel Gafoor Haddad , Mohammed B. Mohiuddin , Igor Boiko , Yahya Zweiri

Video Large Language Models (Video-LLMs) have shown strong video understanding, yet their application to long-form videos remains constrained by limited context windows. A common workaround is to compress long videos into a handful of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Yun Wang , Long Zhang , Jingren Liu , Jiaqi Yan , Zhanjie Zhang , Jiahao Zheng , Ao Ma , Run Ling , Xun Yang , Dapeng Wu , Xiangyu Chen , Xuelong Li

Recent studies suggest that Reinforcement Fine-Tuning (RFT) is inherently more resilient to catastrophic forgetting than Supervised Fine-Tuning (SFT). However, whether RFT (e.g., GRPO) can effectively overcome forgetting in challenging…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Meng Lou , Hanzhong Guo , Linwei Chen , Yizhou Yu

Reinforcement learning (RL)-based driver assistance systems seek to improve fuel consumption via continual improvement of powertrain control actions considering experiential data from the field. However, the need to explore diverse…

Robotics · Computer Science 2023-01-04 Habtamu Hailemichael , Beshah Ayalew , Lindsey Kerbel , Andrej Ivanco , Keith Loiselle

Long-horizon multimodal agents depend on external memory; however, similarity-based retrieval often surfaces stale, low-credibility, or conflicting items, which can trigger overconfident errors. We propose Multimodal Memory Agent (MMA),…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 Yihao Lu , Wanru Cheng , Zeyu Zhang , Hao Tang

In sparse reward scenarios of reinforcement learning (RL), the memory mechanism provides promising shortcuts to policy optimization by reflecting on past experiences like humans. However, current memory-based RL methods simply store and…

Machine Learning · Computer Science 2026-05-28 Renye Yan , Yaozhong Gan , You Wu , Junliang Xing , Ling Liangn , Yeshang Zhu , Yimao Cai

Real-world robotic agents must act under partial observability and long horizons, where key cues may appear long before they affect decision making. However, most modern approaches rely solely on instantaneous information, without…

Machine Learning · Computer Science 2026-03-05 Egor Cherepanov , Alexey K. Kovalev , Aleksandr I. Panov

Efficient navigation in dynamic environments is crucial for autonomous robots interacting with moving agents and static obstacles. We present a novel deep reinforcement learning approach that improves robot navigation and interaction with…

Robotics · Computer Science 2025-09-30 Yury Kolomeytsev , Dmitry Golembiovsky

Skill effect models for long-horizon manipulation tasks are prone to failures in conditions not covered by training data distributions. Therefore, enabling robots to reason about and learn from failures is necessary. We investigate the…

Robotics · Computer Science 2025-09-03 Yixuan Huang , Novella Alvina , Mohanraj Devendran Shanthi , Tucker Hermans

Model-based reinforcement learning attempts to use an available or learned model to improve the data efficiency of reinforcement learning. This work proposes a one-step lookback approach that jointly learns the deep incremental model and…

Robotics · Computer Science 2025-02-28 Cong Li