Asynchronous framework with Reptile plus algorithm to meta learn partially observable Markov decision process

Quang Dang Nguyen

doi:10.1007/s10489-020-01748-7

Asynchronous framework with Reptile plus algorithm to meta learn partially observable Markov decision process

2020-07-09

9

PRE

AI

DOI：10.1007/s10489-020-01748-7

原文链接

原文求助

摘要

En 中文

Meta-learning has recently received much attention in a wide variety of deep reinforcement learning (DRL). In non-meta-learning, we have to train a deep neural network as a controller to learn a specific control task from scratch using a large amount of data. This way of training has shown many limitations in handling different related tasks. Therefore, meta-learning on control domains becomes a powerful tool for transfer learning on related tasks. However, it is widely known that meta-learning requires massive computation and training time. This paper will propose a novel DRL framework, which is called HCGF-R2-DDPG (Hybrid CPU/GPU Framework for Reptile+ and Recurrent Deep Deterministic Policy Gradient). HCGF-R2-DDPG will integrate meta-learning into a general asynchronous training architecture. The proposed framework will allow utilising both CPU and GPU to boost the training speed for the meta network initialisation. We will evaluate HCGF-R2-DDPG on various Partially Observable Markov Decision Process (POMDP) domains.

Keyword:

Meta learning

Deep reinforcement learning

Partial observable Markov decision process

Asynchronous framework

Recurrent deep deterministic policy gradient

Asynchronous framework with Reptile plus algorithm to meta learn partially observable Markov decision process

摘要

AI总结

期刊

机构

引用论文