第10期：DeepRL每日论文快报

DeepRL每日论文快报

来源自：arxiv.com

编辑：DeepRL

时间：2019-12-13

On-policy Reinforcement Learning with Entropy Regularization

arxiv链接: https://arxiv.org/pdf/1912.01557.pdf

Human-Robot Collaboration via Deep Reinforcement Learning of Real-World Interactions

arxiv链接: https://arxiv.org/pdf/1912.01715.pdf

Iterative Policy-Space Expansion in Reinforcement Learning

arxiv链接: https://arxiv.org/pdf/1912.02532.pdf

Deep Model Compression via Deep Reinforcement Learning

arxiv链接: https://arxiv.org/pdf/1912.02532.pdf

Observational Overfitting in Reinforcement Learning

arxiv链接: https://arxiv.org/pdf/1912.02975.pdf

Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions

arxiv链接: https://arxiv.org/pdf/1912.02875.pdf

Learning Sparse Representations Incrementally in Deep Reinforcement Learning

arxiv链接: https://arxiv.org/pdf/1912.04002.pdf

Entropy Regularization with Discounted Future State Distribution in Policy Gradient Methods

arxiv链接: https://arxiv.org/pdf/1912.05104.pdf

GitHub每日同步更新(欢迎star)

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