Links and help references

The RL-Studio library is an artificial intelligence algorithm programming environment based on learning by reinforcement.

By using standard robotic software such as the ROS communications library and the Gazebo simulator, using the Python programming language, environments can be created where the agent can solve a situation.

Group discussed papers

We have a paper discussion group where we present and discuss papers related to RL and autonomous driving. Here, you can find the references to the already presented papers.

Learning by Cheating (Dian Chen, Brady Zhou, Vladlen Koltun, Philipp Krähenbühl)

[20 oct 2022] Presented by Sergio Paniego.

End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances (Marin Toromanoff, Emilie Wirbel, Fabien Moutarde)

[27 oct 2022] Presented by Rubén Lucas.

End-to-end Driving via Conditional Imitation Learning (Felipe Codevilla, Matthias Müller, Antonio López, Vladlen Koltun and Alexey Dosovitskiy)

[10 nov 2022] Presented by Sergio Paniego.

Reward (Mis) Design for Autonomous Driving (W.Bradley Knox, Alessandro Allievi, Holger Banzhaf, Feliz Schmitt, Peter Stone)

[18 nov 2022] Presented by Pedro Fernández.

Reinforcement Learning-Based Autonomous Driving at Intersections in CARLA Simulator (Rodrigo Gutiérrez-Moreno, Rafael Barea, Elena López-Guillén, Javier Araluce and Luis M. Bergasa)

[21 dec 2022] Presented by Rubén Lucas.

Interpretable End-to-End Urban Autonomous Driving With Latent Deep Reinforcement Learning (Jianyu Chen, Shengo Eben Li, Masayoshi Tomizuka)

[9 mar 2023] Presented by Pedro Fernández.