deep-reinforcement-learning

介绍
前言
- 神经网络
- 研究平台
方法
附录

Powered by GitBook

On this page

方法
Viability of Sub-Task Rewards
Experiments in Multimodal Embeddings
MONTEZUMA’SREVENGE
Dataset Generation
Learning Frame-Command Mappings with Bimodal Network
Run-Time Learning From Natural Language Reward Using Multimodal Embedding
最终结果

Was this helpful?

方法

蒙特祖玛的复仇

Natural Language Guided Reinforcement Learning

PreviousApe-X DQfD Next竞速游戏

Last updated 5 years ago

Was this helpful?