5 papers
On the Inherent Robustness of One-Stage Object Detection against Out-of-Distribution Data
Aitor Martinez-Seras, Javier Del Ser, Aitzol Olivares-Rad +2
Robustness is a fundamental aspect for developing safe and trustworthy models, particularly when they are deployed in the open world. In this work we analyze the inherent capabilit…
Using Offline Data to Speed Up Reinforcement Learning in Procedurally Generated Environments
Alain Andres, Lukas Schäfer, Stefano V. Albrecht +1
One of the key challenges of Reinforcement Learning (RL) is the ability of agents to generalise their learned policy to unseen settings. Moreover, training RL agents requires large…
On the Black-box Explainability of Object Detection Models for Safe and Trustworthy Industrial Applications
Alain Andres, Aitor Martinez-Seras, Ibai Laña +1
In the realm of human-machine interaction, artificial intelligence has become a powerful tool for accelerating data modeling tasks. Object detection methods have achieved outstandi…
Fostering Intrinsic Motivation in Reinforcement Learning with Pretrained Foundation Models
Alain Andres, Javier Del Ser
Exploration remains a significant challenge in reinforcement learning, especially in environments where extrinsic rewards are sparse or non-existent. The recent rise of foundation…
Words as Beacons: Guiding RL Agents with High-Level Language Prompts
Unai Ruiz-Gonzalez, Alain Andres, Pedro G. Bascoy +1
Sparse reward environments in reinforcement learning (RL) pose significant challenges for exploration, often leading to inefficient or incomplete learning processes. To tackle this…