Difference between revisions of "Winter 2018 CS595I Advanced NLP/ML Seminar"
From courses
(→Reinforcement Learning) |
(→Reinforcement Learning) |
||
| Line 17: | Line 17: | ||
===Reinforcement Learning=== | ===Reinforcement Learning=== | ||
| + | * 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 | ||
* Robust Imitation of Diverse Behaviors, Wang et al. 2017, https://arxiv.org/pdf/1707.02747.pdf | * Robust Imitation of Diverse Behaviors, Wang et al. 2017, https://arxiv.org/pdf/1707.02747.pdf | ||
| Line 24: | Line 25: | ||
* Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning, Gu et al., NIPS 2017 https://arxiv.org/abs/1706.00387 | * Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning, Gu et al., NIPS 2017 https://arxiv.org/abs/1706.00387 | ||
* Sequence Level Training with Recurrent Neural Networks https://arxiv.org/pdf/1511.06732.pdf | * Sequence Level Training with Recurrent Neural Networks https://arxiv.org/pdf/1511.06732.pdf | ||
| + | * Hybrid Reward Architecture for Reinforcement Learning, Van Seijen et al., NIPS 2017 https://nips.cc/Conferences/2017/Schedule?showEvent=9314 | ||
| + | * Cold-Start Reinforcement Learning with Softmax Policy Gradient, Ding and Soirut, NIPS 2017 https://nips.cc/Conferences/2017/Schedule?showEvent=9067 | ||
===Generation=== | ===Generation=== | ||
Revision as of 00:27, 4 January 2018
Time: TBD Location: HFH 1132.
If you registered this class, you should contact the instructor to present one paper *and* be the discussant of two papers below.
- Presenter: prepare a short summary of no more than 15 mins of presentation.
- Discussant: 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.
Contents
Word Embeddings
- [VIVEK] Poincare Embeddings for learning Hierarchical Representations, Maximilian Nickel Douwe Kiela https://arxiv.org/pdf/1705.08039.pdf
- Mimicking Word Embeddings using Subword RNNs, Yuval Pinter, Robert Guthrie and Jacob Eisenstein http://aclweb.org/anthology/D17-1010
Relational Learning and Reasoning
- Adversarial Training for Relation Extraction, Yi Wu, David Bamman and Stuart Russell https://people.eecs.berkeley.edu/~russell/papers/emnlp17-relation.pdf
Reinforcement Learning
- 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
- Robust Imitation of Diverse Behaviors, Wang et al. 2017, https://arxiv.org/pdf/1707.02747.pdf
- Programmable Agents, Denil et al., https://arxiv.org/pdf/1706.06383v1.pdf
- Expected Policy Gradients, Kamil Ciosek, Shimon Whiteson, https://arxiv.org/abs/1706.05374
- Reinforcement Learning with Deep Energy-Based Policies Haarnoja et al, ICML 2017 http://proceedings.mlr.press/v70/haarnoja17a/haarnoja17a.pdf
- Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning, Gu et al., NIPS 2017 https://arxiv.org/abs/1706.00387
- Sequence Level Training with Recurrent Neural Networks https://arxiv.org/pdf/1511.06732.pdf
- Hybrid Reward Architecture for Reinforcement Learning, Van Seijen et al., NIPS 2017 https://nips.cc/Conferences/2017/Schedule?showEvent=9314
- Cold-Start Reinforcement Learning with Softmax Policy Gradient, Ding and Soirut, NIPS 2017 https://nips.cc/Conferences/2017/Schedule?showEvent=9067
Generation
- Adversarially Regularized Autoencoders for Generating Discrete Structures, Zhao et al., https://arxiv.org/pdf/1706.04223.pdf
Dialog
- A Deep Reinforcement Learning Chatbot, Serban et al., https://arxiv.org/pdf/1709.02349.pdf
Learning
- Variance-based Regularization with Convex Objectives. Hongseok Namkoong, John Duchi. https://arxiv.org/abs/1610.02581
- Safe and Nested Subgame Solving for Imperfect-Information Games. Noam Brown, Tuomas Sandholm. https://nips.cc/Conferences/2017/Schedule?showEvent=8864
NLP for Computational Social Science
- Analyzing Language in Fake News and Political Fact-Checking, Hannah Rashkin, Eunsol Choi, Jin Yea Jang, Svitlana Volkova and Yejin Choi https://www.cs.jhu.edu/~svitlana/papers/RCYVC_EMNLP2017.pdf
- Human Centered NLP with User Factor Adaptation. Veronica Lynn, Youngseo Son, Vivek Kulkarni, Niranjan Balasubramanian, H Andrew Schwartz, http://www.aclweb.org/anthology/D17-1120
