0
点赞
收藏
分享

微信扫一扫

Loss is its own Reward: Self-Supervision for Reinforcement Learning

夕颜合欢落 2022-07-18 阅读 86
github编程语言

作者用action, reward, state等当做lalbel，进行有监督训练。

 

黄世宇/Shiyu Huang's Personal Page：​​https://huangshiyu13.github.io/​​



举报

相关推荐

领域自适应论文（六十五）：Unsupervised Domain Adaptation through Self-Supervision论文原理

深度学习领域自适应人工智能

Deep Reinforcement Learning from Self-Play in Imperfect-Information Games

深度学习有监督学习数据编程语言

reward model learning papers

数据sed最小化JavaScript前端开发

Playing FPS Games with Deep Reinforcement Learning

不完全信息githubJava编程语言

Incentivizing exploration in reinforcement learning with deep predictive models

github编程语言

《Reinforcement Learning: An Introduction》第8章笔记

kubernetes容器云原生

论文阅读-Policy Optimization for Continuous Reinforcement Learning

sqlite数据库

【ICCV 2015】Active Object Localization with Deep Reinforcement Learning

计算机视觉深度学习机器学习搜索触发器人工智能

深度学习之：强化学习 Reinforcement Learning

深度学习人工智能

从baselines库的common/vec_env/vec_normalize.py看reinforcement learning算法中的reward shape方法

杂谈方差正则化代码编写编程语言
0 条评论