8 papers
Embodied Active Learning under Limited Annotation and Navigation Budget for Object Detection
Hadrien Crassous, Mohamed Yassine Kabouri, Minahil Raza +2
This paper studies how to adapt a computer vision object detector to an unknown environment under both a robot navigation time and annotation budget constraint. Our approach select…
When (and How) to Trust the Expert: Diagnosing Query-Time Expert-Guided Reinforcement Learning
Yann Berthelot, Philippe Preux, Riad Akrour
Many continuous-control problems ship with a competent but suboptimal controller (a tuned PID, a hand-designed gait). A growing family of methods uses such controllers as queryable…
StaQ: a Finite Memory Approach to Discrete Action Policy Mirror Descent
Alena Shilova, Alex Davey, Brahim Driss +1
In Reinforcement Learning (RL), regularization with a Kullback-Leibler divergence that penalizes large deviations between successive policies has emerged as a popular tool both in…
PB: Preference Space Exploration via Population-Based Methods in Preference-Based Reinforcement Learning
Brahim Driss, Alex Davey, Riad Akrour
Preference-based reinforcement learning (PbRL) has emerged as a promising approach for learning behaviors from human feedback without predefined reward functions. However, current…
Breiman meets Bellman: Non-Greedy Decision Trees with MDPs
Hector Kohler, Riad Akrour, Philippe Preux
In supervised learning, decision trees are valued for their interpretability and performance. While greedy decision tree algorithms like CART remain widely used due to their comput…
Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programs
Hector Kohler, Quentin Delfosse, Waris Radji +2
There exist applications of reinforcement learning like medicine where policies need to be ''interpretable'' by humans. User studies have shown that some policy classes might be mo…