English
Related papers

Related papers: Staggered Environment Resets Improve Massively Par…

200 papers

We present Variable Experience Rollout (VER), a technique for efficiently scaling batched on-policy reinforcement learning in heterogenous environments (where different environments take vastly different times to generate rollouts) to many…

Machine Learning · Computer Science 2022-10-12 Erik Wijmans , Irfan Essa , Dhruv Batra

In this work, we propose a computationally efficient algorithm for visual policy learning that leverages differentiable simulation and first-order analytical policy gradients. Our approach decouple the rendering process from the computation…

Machine Learning · Computer Science 2025-11-12 Haoxiang You , Yilang Liu , Ian Abraham

While reinforcement learning (RL) provides a framework for learning through trial and error, translating RL algorithms into the real world has remained challenging. A major hurdle to real-world application arises from the development of…

Machine Learning · Computer Science 2022-05-12 Archit Sharma , Rehaan Ahmad , Chelsea Finn

Recent state-of-the-art artificial agents lack the ability to adapt rapidly to new tasks, as they are trained exclusively for specific objectives and require massive amounts of interaction to learn new skills. Meta-reinforcement learning…

Machine Learning · Computer Science 2022-03-23 Zhenshan Bing , Lukas Knak , Fabrice Oliver Robin , Kai Huang , Alois Knoll

Real-world reinforcement learning (RL) environments, whether in robotics or industrial settings, often involve non-visual observations and require not only efficient but also reliable and thus interpretable and flexible RL approaches. To…

Machine Learning · Computer Science 2024-02-19 Moritz Lange , Noah Krystiniak , Raphael C. Engelhardt , Wolfgang Konen , Laurenz Wiskott

Robotic surgery is a rapidly developing field that can greatly benefit from the automation of surgical tasks. However, training techniques such as Reinforcement Learning (RL) require a high number of task repetitions, which are generally…

Robotics · Computer Science 2025-06-04 Diego Dall'Alba , Michał Naskręt , Sabina Kaminska , Przemysław Korzeniowski

Device sizing is a critical yet challenging step in analog and mixed-signal circuit design, requiring careful optimization to meet diverse performance specifications. This challenge is further amplified under process, voltage, and…

Signal Processing · Electrical Eng. & Systems 2025-08-05 Seunggeun Kim , Ziyi Wang , Sungyoung Lee , Youngmin Oh , Hanqing Zhu , Doyun Kim , David Z. Pan

Learning in games has been widely used to solve many cooperative multi-agent problems such as coverage control, consensus, self-reconfiguration or vehicle-target assignment. One standard approach in this domain is to formulate the problem…

Systems and Control · Electrical Eng. & Systems 2022-09-07 Abbasali Koochakzadeh , Yasin Yazıcıoğlu

Despite ample motivation from costly exploration and limited trajectory data, rapidly adapting to new environments with few-shot reinforcement learning (RL) can remain a challenging task, especially with respect to personalized settings.…

Machine Learning · Computer Science 2020-10-13 Michael Zhang

We present Speculative Rollout with Tree-Structured Cache (SRT), a simple, model-free approach to accelerate on-policy reinforcement learning (RL) for language models without sacrificing distributional correctness. SRT exploits the…

Machine Learning · Computer Science 2026-01-15 Chi-Chih Chang , Siqi Zhu , Zhichen Zeng , Haibin Lin , Jiaxuan You , Mohamed S. Abdelfattah , Ziheng Jiang , Xuehai Qian

We propose a new sample-efficient methodology, called Supervised Policy Update (SPU), for deep reinforcement learning. Starting with data generated by the current policy, SPU formulates and solves a constrained optimization problem in the…

Machine Learning · Computer Science 2018-12-27 Quan Vuong , Yiming Zhang , Keith W. Ross

We introduce Random Reward Perturbation (RRP), a novel exploration strategy for reinforcement learning (RL). Our theoretical analyses demonstrate that adding zero-mean noise to environmental rewards effectively enhances policy diversity…

Machine Learning · Computer Science 2025-06-11 Haozhe Ma , Guoji Fu , Zhengding Luo , Jiele Wu , Tze-Yun Leong

While intelligent tutoring systems (ITSs) can use information from past students to personalize instruction, each new student is unique. Moreover, the education problem is inherently difficult because the learning process is only partially…

Machine Learning · Computer Science 2025-11-20 Jeffrey Jiang , Kevin Hong , Emily Kuczynski , Gregory Pottie

We apply reinforcement learning (RL) to robotics tasks. One of the drawbacks of traditional RL algorithms has been their poor sample efficiency. One approach to improve the sample efficiency is model-based RL. In our model-based RL…

Machine Learning · Computer Science 2023-05-16 Adithya Ramesh , Balaraman Ravindran

Scaling reinforcement learning (RL) has shown strong promise for enhancing the reasoning abilities of large language models (LLMs), particularly in tasks requiring long chain-of-thought generation. However, RL training efficiency is often…

Machine Learning · Computer Science 2026-03-25 Yiqi Zhang , Huiqiang Jiang , Xufang Luo , Zhihe Yang , Chengruidong Zhang , Yifei Shen , Dongsheng Li , Yuqing Yang , Lili Qiu , Yang You

Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration. We propose Recovery RL, an algorithm…

Deep reinforcement learning can generate complex control policies, but requires large amounts of training data to work effectively. Recent work has attempted to address this issue by leveraging differentiable simulators. However, inherent…

Machine Learning · Computer Science 2022-04-15 Jie Xu , Viktor Makoviychuk , Yashraj Narang , Fabio Ramos , Wojciech Matusik , Animesh Garg , Miles Macklin

The objective comparison of Reinforcement Learning (RL) algorithms is notoriously complex as outcomes and benchmarking of performances of different RL approaches are critically sensitive to environmental design, reward structures, and…

Machine Learning · Computer Science 2026-03-19 Sinan Ibrahim , Grégoire Ouerdane , Hadi Salloum , Henni Ouerdane , Stefan Streif , Pavel Osinenko

Most parallel neural network training methods assume homogeneous computing resources. For example, synchronous data-parallel SGD suffers from significant synchronization overhead under heterogeneous workloads, often forcing practitioners to…

Machine Learning · Computer Science 2026-02-24 Jihyun Lim , Junhyuk Jo , Chanhyeok Ko , Young Min Go , Jimin Hwa , Sunwoo Lee

Community GPU platforms are emerging as a cost-effective and democratized alternative to centralized GPU clusters for AI workloads, aggregating idle consumer GPUs from globally distributed and heterogeneous environments. However, their…

Networking and Internet Architecture · Computer Science 2025-08-19 Zhiwei Yu , Chengze Du , Heng Xu , Ying Zhou , Bo Liu , Jialong Li