Transformers in reinforcement learning: a survey

P Agarwal, AA Rahman, PL St-Charles… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Transformers have significantly impacted domains like natural language processing,
computer vision, and robotics, where they improve performance compared to other neural …

[HTML][HTML] Image Analysis in Autonomous Vehicles: A Review of the Latest AI Solutions and Their Comparison

M Kozłowski, S Racewicz, S Wierzbicki - Applied Sciences, 2024‏ - mdpi.com
The integration of advanced image analysis using artificial intelligence (AI) is pivotal for the
evolution of autonomous vehicles (AVs). This article provides a thorough review of the most …

Structure in deep reinforcement learning: A survey and open problems

A Mohan, A Zhang, M Lindauer - Journal of Artificial Intelligence Research, 2024‏ - jair.org
Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural
Networks (DNNs) for function approximation, has demonstrated considerable success in …

Dynamics generalisation in reinforcement learning via adaptive context-aware policies

M Beukman, D Jarvis, R Klein… - Advances in Neural …, 2023‏ - proceedings.neurips.cc
While reinforcement learning has achieved remarkable successes in several domains, its
real-world application is limited due to many methods failing to generalise to unfamiliar …

Universal morphology control via contextual modulation

Z **ong, J Beck, S Whiteson - International Conference on …, 2023‏ - proceedings.mlr.press
Learning a universal policy across different robot morphologies can significantly improve
learning efficiency and generalization in continuous control. However, it poses a challenging …

The impact of task underspecification in evaluating deep reinforcement learning

V Jayawardana, C Tang, S Li… - Advances in Neural …, 2022‏ - proceedings.neurips.cc
Abstract Evaluations of Deep Reinforcement Learning (DRL) methods are an integral part of
scientific progress of the field. Beyond designing DRL methods for general intelligence …

Learning long-term crop management strategies with cyclesgym

M Turchetta, L Corinzia, S Sussex… - Advances in neural …, 2022‏ - proceedings.neurips.cc
To improve the sustainability and resilience of modern food systems, designing improved
crop management strategies is crucial. The increasing abundance of data on agricultural …

[HTML][HTML] Contextual reinforcement learning for supply chain management

A Batsis, S Samothrakis - Expert Systems with Applications, 2024‏ - Elsevier
Efficient generalisation in supply chain inventory management is challenging due to a
potential mismatch between the model optimised and objective reality. It is hard to know how …

Generalizing cooperative eco-driving via multi-residual task learning

V Jayawardana, S Li, C Wu, Y Farid… - … on Robotics and …, 2024‏ - ieeexplore.ieee.org
Conventional control, such as model-based control, is commonly utilized in autonomous
driving due to its efficiency and reliability. However, real-world autonomous driving contends …

Reinforcement learning pulses for transmon qubit entangling gates

HN Nguyen, F Motzoi, M Metcalf… - Machine Learning …, 2024‏ - iopscience.iop.org
The utility of a quantum computer is highly dependent on the ability to reliably perform
accurate quantum logic operations. For finding optimal control solutions, it is of particular …