Attention-based experience replay in deep Q-learning

Sie sind hier: Homepage > Suche

Attention-based experience replay in deep Q-learning

Freier Zugriff

RAMICIC, MIRZA / BONARINI, ANDREA

Using neural networks as function approximators in temporal difference reinforcement problems proved to be very effective in dealing with high-dimensionality of input state space, especially in more recent developments such as Deep Q-learning. These approaches share the use of a mechanism, called experience replay, that uniformly samples the previous experiences to a memory buffer to exploit them to re-learn, thus improving the efficiency of the learning process. In order to increase the learning performance, techniques such as prioritized experience and prioritized sampling have been introduced to deal with storing and replaying, respectively, the transitions with larger TD error. In this paper, we present a concept, called Attention-Based Experience REplay (ABERE), concerned with selective focusing of the replay buffer to specific types of experiences, therefore modeling the behavioral characteristics of the learning agent in a single and multi-agent environment. We further explore how different behavioral characteristics influence the performance of agents faced with dynamic environment that is able to become more hostile or benevolent by changing the relative probability to get positive or negative reinforcement.

Zugriff

Download

Exportieren, teilen und zitieren

Dokumentinformationen

Titel :

Attention-based experience replay in deep Q-learning

Beteiligte:

RAMICIC, MIRZA (Autor:in) / BONARINI, ANDREA (Autor:in) / Ramicic, Mirza / Bonarini, Andrea

Erscheinungsdatum :

2017-01-01

DOI :

https://doi.org/10.1145/3055635.3056621

Medientyp :

Aufsatz (Konferenz)

Format :

Elektronische Ressource

Sprache :

Englisch

Schlagwörter :

Congnitive architecture , Deep learning , Deep reinforcement learning , Policy control , Reinforcement learning , Human-Computer Interaction , Computer Networks and Communication , 1707 , Software

Klassifikation :

DDC:

629

Attention-based experience replay in deep Q-learning

Attention-based experience replay in deep Q-learning

Zugriff

Exportieren, teilen und zitieren

Dokumentinformationen

Ähnliche Titel

Zugriff

Seitennavigation

Exportieren, teilen und zitieren