English
Related papers

Related papers: Accelerating Transformers in Online RL

200 papers

A long-standing goal in AI is to develop agents capable of solving diverse tasks across a range of environments, including those never seen during training. Two dominant paradigms address this challenge: (i) reinforcement learning (RL),…

Machine Learning · Computer Science 2025-10-30 Vlad Sobal , Wancong Zhang , Kyunghyun Cho , Randall Balestriero , Tim G. J. Rudner , Yann LeCun

The pretrain-finetuning paradigm in large-scale sequence models has made significant progress in natural language processing and computer vision tasks. However, such a paradigm is still hindered by several challenges in Reinforcement…

Machine Learning · Computer Science 2022-11-16 Runji Lin , Ye Li , Xidong Feng , Zhaowei Zhang , Xian Hong Wu Fung , Haifeng Zhang , Jun Wang , Yali Du , Yaodong Yang

High-fidelity simulation models are widely used to analyze complex stochastic systems, but their high computational cost motivates the development of cheaper surrogate models that approximate the simulation model's input-output…

Machine Learning · Statistics 2026-05-28 Mohammadmahdi Ghasemloo , David J. Eckman , Yaxian Li

Offline reinforcement learning (RL) enables policy optimization using static datasets, avoiding the risks and costs of extensive real-world exploration. However, it struggles with suboptimal offline behaviors and inaccurate value estimation…

Machine Learning · Computer Science 2025-05-20 Minting Pan , Yitao Zheng , Jiajian Li , Yunbo Wang , Xiaokang Yang

Conventional reinforcement learning (RL) needs an environment to collect fresh data, which is impractical when online interactions are costly. Offline RL provides an alternative solution by directly learning from the previously collected…

Machine Learning · Computer Science 2023-03-15 Han Zheng , Xufang Luo , Pengfei Wei , Xuan Song , Dongsheng Li , Jing Jiang

Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficiency, recent work focuses on model-based RL which interleaves…

Machine Learning · Computer Science 2023-06-19 Yi Zhao , Wenshuai Zhao , Rinu Boney , Juho Kannala , Joni Pajarinen

Reinforcement learning (RL) is well known for requiring large amounts of data in order for RL agents to learn to perform complex tasks. Recent progress in model-based RL allows agents to be much more data-efficient, as it enables them to…

Machine Learning · Computer Science 2021-08-17 Remo Sasso , Matthia Sabatelli , Marco A. Wiering

The aim of multi-task reinforcement learning is two-fold: (1) efficiently learn by training against multiple tasks and (2) quickly adapt, using limited samples, to a variety of new tasks. In this work, the tasks correspond to reward…

Machine Learning · Computer Science 2019-11-05 Nicholas C. Landolfi , Garrett Thomas , Tengyu Ma

In machine learning, meta-learning methods aim for fast adaptability to unknown tasks using prior knowledge. Model-based meta-reinforcement learning combines reinforcement learning via world models with Meta Reinforcement Learning (MRL) for…

Robotics · Computer Science 2022-10-10 Karam Daaboul , Joel Ikels , Marius Zöllner

Offline reinforcement learning (RL) aims to learn a policy from a static dataset without further interactions with the environment. Collecting sufficiently large datasets for offline RL is exhausting since this data collection requires…

Artificial Intelligence · Computer Science 2025-10-22 Jongchan Park , Mingyu Park , Donghwan Lee

We study the problem of offline pre-training and online fine-tuning for reinforcement learning from high-dimensional observations in the context of realistic robot tasks. Recent offline model-free approaches successfully use online…

Machine Learning · Computer Science 2024-01-09 Rafael Rafailov , Kyle Hatch , Victor Kolev , John D. Martin , Mariano Phielipp , Chelsea Finn

To enable embodied agents to operate effectively over extended timeframes, it is crucial to develop models that form and access memories to stay contextualized in their environment. In the current paradigm of training transformer-based…

Artificial Intelligence · Computer Science 2025-12-01 Gunshi Gupta , Karmesh Yadav , Zsolt Kira , Yarin Gal , Rahaf Aljundi

Scaling transformers has led to significant breakthroughs in many domains, leading to a paradigm in which larger versions of existing models are trained and released on a periodic basis. New instances of such models are typically trained…

Reinforcement learning is considered as a promising direction for driving policy learning. However, training autonomous driving vehicle with reinforcement learning in real environment involves non-affordable trial-and-error. It is more…

Artificial Intelligence · Computer Science 2017-09-27 Xinlei Pan , Yurong You , Ziyan Wang , Cewu Lu

Offline reinforcement learning (RL) allows learning sequential behavior from fixed datasets. Since offline datasets do not cover all possible situations, many methods collect additional data during online fine-tuning to improve performance.…

Machine Learning · Computer Science 2024-06-13 Mohammadreza Nakhaei , Aidan Scannell , Joni Pajarinen

Deep reinforcement learning has proven to be a great success in allowing agents to learn complex tasks. However, its application to actual robots can be prohibitively expensive. Furthermore, the unpredictability of human behavior in…

Robotics · Computer Science 2019-08-16 Mohammad Thabet , Massimiliano Patacchiola , Angelo Cangelosi

We address the problem of agile 1v1 quadrotor pursuit-evasion, where a pursuer and an evader learn to outmaneuver each other through reinforcement learning (RL). Such settings face two major challenges: non-stationarity, since each agent's…

Robotics · Computer Science 2025-09-16 Alejandro Sanchez Roncero , Yixi Cai , Olov Andersson , Petter Ogren

Urban autonomous driving decision making is challenging due to complex road geometry and multi-agent interactions. Current decision making methods are mostly manually designing the driving policy, which might result in sub-optimal solutions…

Machine Learning · Computer Science 2019-10-23 Jianyu Chen , Bodi Yuan , Masayoshi Tomizuka

Current control algorithms for aerial robots struggle with robustness in dynamic environments and adverse conditions. Model-based reinforcement learning (RL) has shown strong potential in handling these challenges while remaining…

Robotics · Computer Science 2025-11-25 Eashan Vytla , Bhavanishankar Kalavakolanu , Andrew Perrault , Matthew McCrink

Meta-reinforcement learning (RL) methods can meta-train policies that adapt to new tasks with orders of magnitude less data than standard RL, but meta-training itself is costly and time-consuming. If we can meta-train on offline data, then…

Machine Learning · Computer Science 2022-07-08 Vitchyr H. Pong , Ashvin Nair , Laura Smith , Catherine Huang , Sergey Levine
‹ Prev 1 4 5 6 7 8 10 Next ›