Similarity metrics for Different Market Scenarios in Abides

no code implementations • 20 Jul 2021 • Diego Pino, Javier García, Fernando Fernández, Svitlana S Vyetrenko

Regarding the second one, this paper uses Probabilistic Policy Reuse to balance the exploitation/exploration in the learning of a new financial MDP according to the similarity of the previous financial MDPs whose knowledge is reused.

Transfer Learning

A Taxonomy of Similarity Metrics for Markov Decision Processes

no code implementations • 8 Mar 2021 • Álvaro Visús, Javier García, Fernando Fernández

Although the notion of task similarity is potentially interesting in a wide range of areas such as curriculum learning or automated planning, it has mostly been tied to transfer learning.

Reinforcement Learning (RL) Transfer Learning

Disturbing Reinforcement Learning Agents with Corrupted Rewards

no code implementations • 12 Feb 2021 • Rubén Majadas, Javier García, Fernando Fernández

Reinforcement Learning (RL) algorithms have led to recent successes in solving complex games, such as Atari or Starcraft, and to a huge impact in real-world applications, such as cybersecurity or autonomous driving.

Autonomous Driving reinforcement-learning +2