Paper Reviews

weekly reinforcement learning paper reviews

Reviewed Papers

• Nov 22 2017

  • 2017, A Distributional Perspective on Reinforcement Learning PAPER NOTE - review by Woongwon
  • 2014, Deterministic Policy Gradient Algorithms PAPER NOTE - review by Chanwoong

• Nov 29 2017

  • 2010, On a Connection between Importance Sampling and the Likelihood Ratio Policy Gradient PAPER NOTE - review by Brian

• Dec 06 2017

  • 2015, Prioritized Experience Replay PAPER NOTE - review by Chanwoong
  • 2017, Curiosity-driven Exploration by Self-supervised Prediction PAPERNOTE - review by Youngmoo

• Dec 20 2017

  • 2016, Sample Efficient Actor-Critic with Experience Replay PAPER - review by Brian
  • 2017, Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning[EMNLP 2017] PAPER NOTE- review by Hyeokreal

• Dec 30 2017

  • 2015, Trust Region Policy Optimization PAPER NOTE - review by Woongwon

• Jan 3 2018

  • 2017, Deep Q-learning from Demonstrations PAPER - review by Chris Hoyean Song

Interesting Papers

• 2016, Personalizing a Dialogue System with Transfer Reinforcement Learning PAPER
• 2016, Policy Networks with Two-Stage Training for Dialogue Systems PAPER
• 2016, Deep Reinforcement Learning for Dialogue Generation PAPER
• 2017, Learning to Act by Predicting the Future PAPER
• 2017, Proximal Policy Optimization Algorithms PAPER
• 2017, Efficient Parallel Methods for Deep Reinforcement Learning PAPER NOTE