Three papers about reinforcement learning from our group were presented at AAMAS 2020

News - 15 May 2020 - Communication

All the talks are available on the conference website.

At the main conference:

  • Generalized Optimistic Q-Learning with Provable Efficiency by Grigory Neustroev and Mathijs M. de Weerdt [talk] [paper]
  • Safe Policy Improvement with an Estimated Baseline Policy by Thiago D. Simão, Romain Laroche and Rémi Tachet des Combes: [talk] [paper]

At the Adaptive and Learning Agents Workshop:

Interval Q-Learning: Balancing Deep and Wide Exploration by Grigory Neustroev, Canmanie T. Ponnambalam, Mathijs M. de Weerdt and Matthijs T. J. Spaan: [talk] [paper]