第14期：深度强化学习《论文快报》

DeepRL论文快报

来源自：arxiv.com

编辑：DeepRL

Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping

arxiv链接: https://arxiv.org/pdf/2001.07527.pdf

Reinforcement Learning with Probabilistically Complete Exploration

arxiv链接:https://arxiv.org/pdf/2001.06940.pdf

Algorithms in Multi-Agent Systems: A Holistic Perspective from Reinforcement Learning and Game Theory

arxiv链接: https://arxiv.org/pdf/2001.06487.pdf

Local Policy Optimization for Trajectory-Centric Reinforcement Learning

arxiv链接: https://arxiv.org/pdf/2001.08092.pdf

On Simple Reactive Neural Networks for Behaviour-Based Reinforcement Learning

arxiv链接: https://arxiv.org/pdf/2001.07973.pdf

Graph Constrained Reinforcement Learning for Natural Language Action Spaces

arxiv链接: https://arxiv.org/pdf/2001.08837.pdf

Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning

arxiv链接: https://arxiv.org/pdf/2001.09684.pdf

Active Task-Inference-Guided Deep Inverse Reinforcement Learning

arxiv链接: https://arxiv.org/pdf/2001.09227.pdf

GitHub每日同步更新(欢迎star)

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

完