English
Related papers

Related papers: Residual Pathway Priors for Soft Equivariance Cons…

200 papers

Robust Markov Decision Processes (RMDPs) have received significant research interest, offering an alternative to standard Markov Decision Processes (MDPs) that often assume fixed transition probabilities. RMDPs address this by optimizing…

Machine Learning · Computer Science 2024-05-06 Xinyi Ni , Lifeng Lai

Safety and robustness are two desired properties for any reinforcement learning algorithm. CMDPs can handle additional safety constraints and RMDPs can perform well under model uncertainties. In this paper, we propose to unite these two…

Machine Learning · Computer Science 2021-08-21 Reazul Hasan Russel , Mouhacine Benosman , Jeroen Van Baar , Radu Corcodel

Random backpropagation (RBP) is a variant of the backpropagation algorithm for training neural networks, where the transpose of the forward matrices are replaced by fixed random matrices in the calculation of the weight updates. It is…

Machine Learning · Computer Science 2017-12-25 Pierre Baldi , Peter Sadowski , Zhiqin Lu

Markov decision processes (MDPs) are a standard model for sequential decision-making problems and are widely used across many scientific areas, including formal methods and artificial intelligence (AI). MDPs do, however, come with the…

Artificial Intelligence · Computer Science 2024-12-11 Marnix Suilen , Thom Badings , Eline M. Bovy , David Parker , Nils Jansen

As we deploy reinforcement learning agents to solve increasingly challenging problems, methods that allow us to inject prior knowledge about the structure of the world and effective solution strategies becomes increasingly important. In…

The increasing demand for autonomous systems in complex and dynamic environments has driven significant research into intelligent path planning methodologies. For decades, graph-based search algorithms, linear programming techniques, and…

Neural processes are a family of models which use neural networks to directly parametrise a map from data sets to predictions. Directly parametrising this map enables the use of expressive neural networks in small-data problems where neural…

Machine Learning · Statistics 2024-08-20 Wessel P. Bruinsma

This paper presents a novel approach that combines the advantages of both model-based and learning-based frameworks to achieve robust locomotion. The residual modules are integrated with each corresponding part of the model-based framework,…

Robotics · Computer Science 2025-07-25 Min-Gyu Kim , Dongyun Kang , Hajun Kim , Hae-Won Park

Recently, the applications of the methodologies of Reinforcement Learning (RL) to NP-Hard Combinatorial optimization problems have become a popular topic. This is essentially due to the nature of the traditional combinatorial algorithms,…

Optimization and Control · Mathematics 2022-08-02 Simone Foa , Corrado Coppola , Giorgio Grani , Laura Palagi

In this paper, we focus on the problem of robustifying reinforcement learning (RL) algorithms with respect to model uncertainties. Indeed, in the framework of model-based RL, we propose to merge the theory of constrained Markov decision…

Machine Learning · Computer Science 2020-10-13 Reazul Hasan Russel , Mouhacine Benosman , Jeroen Van Baar

Reinforcement learning (RL) has shown great potential in enabling quadruped robots to perform agile locomotion. However, directly training policies to simultaneously handle dual extreme challenges, i.e., extreme underactuation and extreme…

Robotics · Computer Science 2025-07-03 Ziang Zheng , Guojian Zhan , Shiqi Liu , Yao Lyu , Tao Zhang , Shengbo Eben Li

Autonomous racing presents a complex environment requiring robust controllers capable of making rapid decisions under dynamic conditions. While traditional controllers based on tire models are reliable, they often demand extensive tuning or…

Robotics · Computer Science 2025-02-07 Edoardo Ghignone , Nicolas Baumann , Cheng Hu , Jonathan Wang , Lei Xie , Andrea Carron , Michele Magno

In the context of continual learning, prototypes-as representative class embeddings-offer advantages in memory conservation and the mitigation of catastrophic forgetting. However, challenges related to semantic drift and prototype…

Machine Learning · Computer Science 2023-11-14 Zhuowei Li , Long Zhao , Zizhao Zhang , Han Zhang , Di Liu , Ting Liu , Dimitris N. Metaxas

Attention-based sequential recommendation methods have shown promise in accurately capturing users' evolving interests from their past interactions. Recent research has also explored the integration of reinforcement learning (RL) into these…

Machine Learning · Computer Science 2024-04-19 Melissa Mozifian , Tristan Sylvain , Dave Evans , Lili Meng

Reinforcement learning (RL) faces challenges in trajectory planning for urban automated driving due to the poor convergence of RL and the difficulty in designing reward functions. Consequently, few RL-based trajectory planning methods can…

Robotics · Computer Science 2025-07-17 Di Zeng , Ling Zheng , Xiantong Yang , Yinong Li

Balancing the trade-off between safety and efficiency is of significant importance for path planning under uncertainty. Many risk-aware path planners have been developed to explicitly limit the probability of collision to an acceptable…

Robotics · Computer Science 2022-10-26 Fei Meng , Liangliang Chen , Han Ma , Jiankun Wang , Max Q. -H. Meng

Using rough path techniques, we provide a priori estimates for the output of Deep Residual Neural Networks in terms of both the input data and the (trained) network weights. As trained network weights are typically very rough when seen as…

Machine Learning · Computer Science 2023-02-22 Christian Bayer , Peter K. Friz , Nikolas Tapia

Aligning large language models with human preferences is critical for creating reliable and controllable AI systems. A human preference can be visualized as a high-dimensional vector where different directions represent trade-offs between…

Computation and Language · Computer Science 2026-02-26 Ruochen Mao , Yuling Shi , Xiaodong Gu , Jiaheng Wei

We study robust Markov decision processes (RMDPs) with non-rectangular uncertainty sets, which capture interdependencies across states unlike traditional rectangular models. While non-rectangular robust policy evaluation is generally…

Artificial Intelligence · Computer Science 2025-02-14 Navdeep Kumar , Adarsh Gupta , Maxence Mohamed Elfatihi , Giorgia Ramponi , Kfir Yehuda Levy , Shie Mannor

Radio map (RM) reconstruction is essential for environment-aware wireless networks, but practical measurements are often collected along mobility trajectories rather than randomly scattered over the target region. Such trajectory-sampled…

Signal Processing · Electrical Eng. & Systems 2026-05-08 Jiawen Zhang , Zhiyuan Jiang , Sheng Zhou , Zhisheng Niu