第13期：深度强化学习《论文快报》

DeepRL论文快报

来源自：arxiv.com

编辑：DeepRL

Direct and indirect reinforcement learning

arxiv链接: https://arxiv.org/pdf/1912.10600.pdf

Parameterized Indexed Value Function for Efficient Exploration in Reinforcement Learning

arxiv链接: https://arxiv.org/pdf/1912.10577.pdf

Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics

arxiv链接: https://arxiv.org/pdf/2001.00449.pdf

Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies

arxiv链接: https://arxiv.org/pdf/2001.00248.pdf

Long-Term Visitation Value for Deep Exploration in Sparse Reward Reinforcement Learning

arxiv链接: https://arxiv.org/pdf/2001.00119.pdf

Optimal Options for Multi-Task Reinforcement Learning Under Time Constraints

arxiv链接: https://arxiv.org/pdf/2001.01620.pdf

MushroomRL: Simplifying Reinforcement Learning Research

arxiv链接: https://arxiv.org/pdf/2001.01102.pdf

GitHub每日同步更新(欢迎star)

https://github.com/NeuronDance/DeepRL/tree/master/DRL-PaperDaily