Transformers are Sample-Efficient World Models

1 code implementation • 1 Sep 2022 • Vincent Micheli, Eloi Alonso, François Fleuret

Deep reinforcement learning agents are notoriously sample inefficient, which considerably limits their application to real-world problems.

Atari Games 100k reinforcement-learning +1

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

no code implementations • 17 Feb 2022 • Anssi Kanervisto, Stephanie Milani, Karolis Ramanauskas, Nicholay Topin, Zichuan Lin, Junyou Li, Jianing Shi, Deheng Ye, Qiang Fu, Wei Yang, Weijun Hong, Zhongyue Huang, Haicheng Chen, Guangjun Zeng, Yue Lin, Vincent Micheli, Eloi Alonso, François Fleuret, Alexander Nikulin, Yury Belousov, Oleg Svidchenko, Aleksei Shpilman

With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers.

Reinforcement Learning Agents for Ubisoft's Roller Champions

no code implementations • 10 Dec 2020 • Nancy Iskander, Aurelien Simoni, Eloi Alonso, Maxim Peter

In recent years, Reinforcement Learning (RL) has seen increasing popularity in research and popular culture.

Cultural Vocal Bursts Intensity Prediction reinforcement-learning +1

Deep Reinforcement Learning for Navigation in AAA Video Games

no code implementations • 9 Nov 2020 • Eloi Alonso, Maxim Peter, David Goumard, Joshua Romoff

We test our approach on complex 3D environments in the Unity game engine that are notably an order of magnitude larger than maps typically used in the Deep RL literature.

Navigate reinforcement-learning +2

Discrete and Continuous Action Representation for Practical RL in Video Games

1 code implementation • 23 Dec 2019 • Olivier Delalleau, Maxim Peter, Eloi Alonso, Adrien Logut

While most current research in Reinforcement Learning (RL) focuses on improving the performance of the algorithms in controlled environments, the use of RL under constraints like those met in the video game industry is rarely studied.

Control with Prametrised Actions Reinforcement Learning (RL)

Adversarial Generation of Handwritten Text Images Conditioned on Sequences

1 code implementation • 1 Mar 2019 • Eloi Alonso, Bastien Moysset, Ronaldo Messina

State-of-the-art offline handwriting text recognition systems tend to use neural networks and therefore require a large amount of annotated data to be trained.