【强化学习资源集合】Awesome Reinforcement Learning

资源标题

强化学习整合：Awesome Reinforcement Learning

资源列表

代码
理论研究
应用
教程
在线样例
开源强化学习平台

成为VIP会员查看完整内容

知识荟萃

精品入门和进阶教程、论文和代码整理等

查看相关VIP内容、论文、资讯等

Performer · Google DeepMind · INTERACT · 对比学习 · 强化学习 ·

2020 年 4 月 28 日

CURL: Contrastive Unsupervised Representations for Reinforcement Learning

Aravind Srinivas,Michael Laskin,Pieter Abbeel

from arxiv, First two authors contributed equally, website: https://mishalaskin.github.io/curl code: https://github.com/MishaLaskin/curl

We present CURL: Contrastive Unsupervised Representations for Reinforcement Learning. CURL extracts high-level features from raw pixels using contrastive learning and performs off-policy control on top of the extracted features. CURL outperforms prior pixel-based methods, both model-based and model-free, on complex tasks in the DeepMind Control Suite and Atari Games showing 1.9x and 1.6x performance gains at the 100K environment and interaction steps benchmarks respectively. On the DeepMind Control Suite, CURL is the first image-based algorithm to nearly match the sample-efficiency and performance of methods that use state-based features.

专知，提供专业可信的知识分发服务，让认知协作更快更好！

Deep Reinforcement Learning via Policy Optimization

成为VIP会员查看完整内容

强化学习 · 专知 · 算法 · GitHub · 人工智能 ·

2019 年 9 月 11 日

【资源】强化学习实践教程

专知

专知-连接人与知识，专信认知，创享美好。我们致力于利用大数据人工智能技术为用户提供优质内容与知识服务。在这里，关注获取专知的团队、技术、产品、业务等动态信息，一起成长！

【导读】本文为大家推荐一份强化学习算法的实践教程，希望对大家有所帮助。原始链接： https://github.com/yandexdataschool/Practical_RL -END- 专 · 知专知，专业可信的人工智能知识分发，

Machine Learning · 专知 · GitHub · 人工智能 · AI ·

2019 年 5 月 29 日

【资源推荐】Machine Learning基础学习资源汇总

专知

【导读】本文为大家推荐一份Machine Learning原理的资源列表内容。

Performance · 主动学习 · 强化学习 · 泛化误差 · 泛化理论 ·

2019 年 1 月 8 日

Risk-Aware Active Inverse Reinforcement Learning

Daniel S. Brown,Yuchen Cui,Scott Niekum

from arxiv, In proceedings of Conference on Robot Learning (CoRL) 2018

Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these strategies directly minimize the performance risk of the policy the robot is learning. Utilizing recent advances in performance bounds for inverse reinforcement learning, we propose a risk-aware active inverse reinforcement learning algorithm that focuses active queries on areas of the state space with the potential for large generalization error. We show that risk-aware active learning outperforms standard active IRL approaches on gridworld, simulated driving, and table setting tasks, while also providing a performance-based stopping criterion that allows a robot to know when it has received enough demonstrations to safely perform a task.