104 citations · 110 across the 6 of their papers we have counts for
3 papers · 1 filter
Reward Function Design for Crowd Simulation via Reinforcement Learning
Ariel Kwiatkowski, Vicky Kalogeiton, Julien Pettré +1
Crowd simulation is important for video-games design, since it enables to populate virtual worlds with autonomous avatars that navigate in a human-like manner. Reinforcement learni…
Properties of pedestrians walking in line without density constraint
Cécile Appert-Rolland, Anne-Hélène Olivier, Julien Pettré
This article deals with the experimental study of pedestrian behaviours in some situations of one-dimensional traffic. Participants were pre-organized in a line, and asked to walk…
UGAE: A Novel Approach to Non-exponential Discounting
Ariel Kwiatkowski, Vicky Kalogeiton, Julien Pettré +1
The discounting mechanism in Reinforcement Learning determines the relative importance of future and present rewards. While exponential discounting is widely used in practice, non-…