Generative Memory for Lifelong Reinforcement Learning

02/22/2019
by   Aswin Raghavan, et al.
0

Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience. We leverage current understanding of biological memory transfer to arrive at AI algorithms for memory consolidation and replay. In this paper, we propose the use of generative memory that can be recalled in batch samples to train a multi-task agent in a pseudo-rehearsal manner. We show results motivating the need for task-agnostic separation of latent space for the generative memory to address issues of catastrophic forgetting in lifelong learning.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

09/21/2021

Learning offline: memory replay in biological and artificial reinforcement learning

Learning to act in an environment to maximise rewards is among the brain...
11/26/2021

Latent Space based Memory Replay for Continual Learning in Artificial Neural Networks

Memory replay may be key to learning in biological brains, which manage ...
03/11/2019

Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay

Despite huge success, deep networks are unable to learn effectively in s...
07/15/2019

A Dual Memory Structure for Efficient Use of Replay Memory in Deep Reinforcement Learning

In this paper, we propose a dual memory structure for reinforcement lear...
04/27/2020

A general approach to progressive learning

In biological learning, data is used to improve performance on the task ...
04/27/2018

How does the AI understand what's going on

Most researchers regard AI as a static function without memory. This is ...
04/27/2020

A general approach to progressive intelligence

In biological learning, data is used to improve performance on the task ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.