Continual and Multi-task Reinforcement Learning With Shared Episodic Memory
By Artyom Y. Sorokin, Mikhail S. Burtsev. 2019
5 citations recorded by the source corpus.
Episodic memory plays an important role in the behavior of animals and humans. It allows the accumulation of information about current state of the environment in a task-agnostic way. This episodic representation can be later accessed by down-stream tasks in order to make their execution more efficient. In this work, we introduce the neural architecture with shared episodic memory (SEM) for learning and the sequential execution of multiple tasks. We explicitly split the encoding of episodic memory and task-specific memory into separate recurrent sub-networks. An agent augmented with SEM was able to effectively reuse episodic knowledge collected during other tasks to improve its policy on a current task in the Taxi problem. Repeated use of episodic representation in continual learning experiments facilitated acquisition of novel skills in the same environment.
Subfields: Artificial Intelligence, Cognitive Neuroscience, Computational Theory and Mathematics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mehrdad Farajtabar
- Ang Li
- Navid Azizan
- Alex Mott
- Seyed Iman Mirzadeh
- Razvan Pascanu
- Hassan Ghasemzadeh
- Youngjae Min
In Cognitive Neuroscience
In Computational Theory and Mathematics
Citations in the corpus
- Orthogonal Gradient Descent for Continual Learning (2019, background): “Multi-task learning (Sorokin and Burtsev, 2019), curriculum learning (Bengio et al., 2009), and transfer learning (Pan and Yang, 2009; Li et al., 2019a) are other related areas helpful to develop better continual learning machines that do not catas-trophically forget previous experiences.”