Difference between revisions of "Winter 2018 CS595I Advanced NLP/ML Seminar"

From courses
Jump to: navigation, search
Line 37: Line 37:
  
 
===Reinforcement Learning===
 
===Reinforcement Learning===
*Counterfactual Multi−Agent Policy Gradients",  Foerster et al., AAAI 2018, Outstanding Student Paper, http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/foersteraaai18.pdf
+
* NEURAL MAP: STRUCTURED MEMORY FOR DEEP REINFORCEMENT LEARNING, Parisotto and Salakhutdinov, ICLR 2018  https://arxiv.org/pdf/1702.08360.pdf
 +
* Counterfactual Multi−Agent Policy Gradients",  Foerster et al., AAAI 2018, Outstanding Student Paper, http://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/foersteraaai18.pdf
 
* Shallow Updates for Deep Reinforcement Learning, Levine et al., NIPS 2017 https://nips.cc/Conferences/2017/Schedule?showEvent=9098
 
* Shallow Updates for Deep Reinforcement Learning, Levine et al., NIPS 2017 https://nips.cc/Conferences/2017/Schedule?showEvent=9098
 
* Imagination-Augmented Agents for Deep Reinforcement Learning Racanière et al., NIPS 2017 https://nips.cc/Conferences/2017/Schedule?showEvent=10081
 
* Imagination-Augmented Agents for Deep Reinforcement Learning Racanière et al., NIPS 2017 https://nips.cc/Conferences/2017/Schedule?showEvent=10081

Revision as of 19:02, 29 January 2018

Time: Monday 5-6pm, starting 01/22. Location: HFH 1132.

If you registered this class, you should contact the instructor to present one paper *and* be the discussant of one paper below.

  • Presenter: prepare a short summary of no more than 15 mins of presentation.
  • Discussant: by presenting a paper in one session, you automatically become the discussant of the other paper. Please prepare two questions for discussion about the paper.

If you don't present or lead the discussion, you will then need to write a 2-page final report in ICML 2018 style, comparing any two of the papers below. Due: TBD to william@cs.ucsb.edu.

  • 03/05
  • 03/12

Reinforcement Learning

Generation

Learning

NLP for Computational Social Science