English
Related papers

Related papers: ABPT: Amended Backpropagation through Time with Pa…

200 papers

Fine-tuning and inference with large Language Models (LM) are generally known to be expensive. Parameter-efficient fine-tuning over pretrained LMs reduces training memory by updating a small number of LM parameters but does not improve…

Computation and Language · Computer Science 2024-06-05 Bowen Zhao , Hannaneh Hajishirzi , Qingqing Cao

We study the corruption-robustness of in-context reinforcement learning (ICRL), focusing on the Decision-Pretrained Transformer (DPT, Lee et al., 2023). To address the challenge of reward poisoning attacks targeting the DPT, we propose a…

Machine Learning · Computer Science 2025-09-30 Paulius Sasnauskas , Yiğit Yalın , Goran Radanović

Parallel training methods are increasingly relevant in machine learning (ML) due to the continuing growth in model and dataset sizes. We propose a variant of the Additively Preconditioned Trust-Region Strategy (APTS) for training deep…

Machine Learning · Computer Science 2025-02-10 Samuel A. Cruz Alegría , Ken Trotti , Alena Kopaničáková , Rolf Krause

Despite Proximal Policy Optimization (PPO) dominating policy gradient methods -- from robotic control to game AI -- its static trust region forces a brittle trade-off: aggressive clipping stifles early exploration, while late-stage updates…

Machine Learning · Computer Science 2025-05-26 Ben Rahman

Bidirectional thrust grants quadrotors a second equilibrium condition and increased control authority, expanding the envelope of possible aggressive maneuvers and enabling inverted flight, perching, and sensing. Prior geometric control…

Humans are remarkably data-efficient when adapting to new unseen conditions, like driving a new car. In contrast, modern robotic control systems, like neural network policies trained using Reinforcement Learning (RL), are highly specialized…

Robotics · Computer Science 2026-04-07 Jonas Eschmann , Dario Albani , Giuseppe Loianno

Backpropagation through time (BPTT) is the de facto standard for training recurrent neural networks (RNNs), but it is non-causal and non-local. Real-time recurrent learning is a causal alternative, but it is highly inefficient. Recently,…

Machine Learning · Computer Science 2024-10-10 Guillermo Martín-Sánchez , Sander Bohté , Sebastian Otte

Policy gradients-based reinforcement learning has proven to be a promising approach for directly optimizing non-differentiable evaluation metrics for language generation tasks. However, optimizing for a specific metric reward leads to…

Computation and Language · Computer Science 2020-11-17 Ramakanth Pasunuru , Han Guo , Mohit Bansal

We consider the bandit problem of selecting $K$ out of $N$ arms at each time step. The reward can be a non-linear function of the rewards of the selected individual arms. The direct use of a multi-armed bandit algorithm requires choosing…

Machine Learning · Computer Science 2026-02-16 Mridul Agarwal , Vaneet Aggarwal , Christopher J. Quinn , Abhishek Umrawal

The Alternating Direction Method of Multipliers (ADMM) is a widely used method for structured convex optimization, and its practical performance depends strongly on the choice of penalty and relaxation parameters. Motivated by settings such…

Optimization and Control · Mathematics 2026-04-30 Junan Lin , Paul J. Goulart , Luca Furieri

Preference-based Reinforcement Learning (PbRL) enables policy learning through simple queries comparing trajectories from a single policy. While human responses to these queries make it possible to learn policies aligned with human…

Robotics · Computer Science 2026-01-22 Yuki Kadokawa , Jonas Frey , Takahiro Miki , Takamitsu Matsubara , Marco Hutter

The growing size of datasets and deep learning models has made faster and memory-efficient training crucial. Reversible transformers have recently been introduced as an exciting new method for extremely memory-efficient training, but they…

Machine Learning · Computer Science 2023-06-16 Tyler Zhu , Karttikeya Mangalam

Inverse reinforcement learning is the problem of inferring a reward function from an optimal policy or demonstrations by an expert. In this work, it is assumed that the reward is expressed as a reward machine whose transitions depend on…

Machine Learning · Computer Science 2025-10-23 Mohamad Louai Shehab , Antoine Aspeel , Necmiye Ozay

Traversing narrow gates presents a significant challenge and has become a standard benchmark for evaluating agile and precise quadrotor flight. Traditional modularized autonomous flight stacks require extensive design and parameter tuning,…

Robotics · Computer Science 2026-03-06 Tianchen Sun , Bingheng Wang , Nuthasith Gerdpratoom , Longbin Tang , Yichao Gao , Lin Zhao

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

Model-free reinforcement learning (RL) has enabled adaptable and agile quadruped locomotion; however, policies often converge to a single gait, leading to suboptimal performance. Traditionally, Model Predictive Control (MPC) has been…

Robotics · Computer Science 2025-10-27 Prakrut Kotecha , Ganga Nair B , Shishir Kolathaya

Personalizing diffusion models using limited data presents significant challenges, including overfitting, loss of prior knowledge, and degradation of text alignment. Overfitting leads to shifts in the noise prediction distribution,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-04 JungWoo Chae , Jiyoon Kim , JaeWoong Choi , Kyungyul Kim , Sangheum Hwang

Control design for robotic systems is complex and often requires solving an optimization to follow a trajectory accurately. Online optimization approaches like Model Predictive Control (MPC) have been shown to achieve great tracking…

This paper presents a new parameter estimation algorithm for the adaptive control of a class of time-varying plants. The main feature of this algorithm is a matrix of time-varying learning rates, which enables parameter estimation error…

Optimization and Control · Mathematics 2021-11-18 Joseph E. Gaudio , Anuradha M. Annaswamy , Eugene Lavretsky , Michael A. Bolender

In Reinforcement Learning (RL), multi-armed Bandit (MAB) problems have found applications across diverse domains such as recommender systems, healthcare, and finance. Traditional MAB algorithms typically assume stationary reward…

Artificial Intelligence · Computer Science 2024-10-10 Gustavo de Freitas Fonseca , Lucas Coelho e Silva , Paulo André Lima de Castro