CreateAMind

492 篇文章
28 人订阅

全部文章

用户1908973

Control is important! model predictive control mpc.pytorch lib

Optimal control is a widespread field that involve finding an optimal sequence o...

1025
用户1908973

强化学习的 bayes 探索

1 openai RND:https://blog.openai.com/reinforcement-learning-with-prediction-base...

955
用户1908973

模仿学习 比较图

ONE-SHOT HIGH-FIDELITY IMITATION: TRAINING LARGE-SCALE DEEP NETS WITH RL

822
用户1908973

无监督学习 比较图

Luke Metz Google Brain lmetz@google.com Niru Maheswaranathan Google Brain nirum...

571
用户1908973

Model-Based 两篇paper

Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based C...

813
用户1908973

逆强化学习几篇论文笔记

1444
用户1908973

empower EMI 笔记

empower blog:https://navneet-nmk.github.io/2018-08-26-empowerment/

913
用户1908973

4篇前沿强化学习论文

HIERARCHICAL VISUOMOTOR CONTROL OF HUMANOIDS

823
用户1908973

A Tutorial on Energy-Based Learning

Yann LeCun, Sumit Chopra, Raia Hadsell, Marc’Aurelio Ranzato, and Fu Jie Huang T...

743
用户1908973

Disentangled的假设的探讨

Francesco Locatello, Stefan Bauer, Mario Lucic, Sylvain Gelly, Bernhard Schölkop...

562
用户1908973

语言的信息瓶颈分析

Efficient human-like semantic representations via the Information Bottleneck pri...

722
用户1908973

Towards a Definition of Disentangled Representations

Towards a Definition of Disentangled Representations Irina Higgins∗ , David Amos...

862
用户1908973

强文!LEARNING ACTIONABLE REPRESENTATIONS WITH GOAL.. POLICIES

LEARNING ACTIONABLE REPRESENTATIONS WITH GOAL-CONDITIONED POLICIES

872
用户1908973

通俗易懂 empowered RL

Inspired by examples from the animal kingdom, social sciences and games the ...

681
用户1908973

互信息 强化学习探索 两篇paper

Hyoungseok Kim, Jaekyeom Kim, Yeonwoo Jeong, Sergey Levine, Hyun Oh Song

793
用户1908973

Yoshua Bengio清华演讲ppt 等其他演讲ppt

http://www.iro.umontreal.ca/~bengioy/yoshua_en/talks.html

703
用户1908973

AI尝试做判断题和填空题的效果

code: https://github.com/createamind/keras-cpcgan

783
用户1908973

NORL(near-optimal representation learning for hierarchical RL)

1173
用户1908973

面试论文:cpc-hrl 很难

https://github.com/tensorflow/models/tree/master/research/efficient-hrl

1133
用户1908973

CPC(representation learning with contrastive predctive coding)

摘要: 监督学习在很多应用方面有了巨大的进步,但是非监督学习却没有如此广的应用,非监督学习是人工智能方面非常重要也非常具有挑战性的领域。这篇论文提出了 cons...

1033

扫码关注云+社区