Yang Gao

Yang Gao, Ph.D.

Postdoctoral researcher

+49 6151 16-21677
+49 6151 16-25295

Personal Homepage

Hochschulstraße 10
64289 Darmstadt

Office: S2|02 B106

More information

I joined the UKP lab in June 2017 as a postdoc researcher. I obtained my PhD degree from Imperial College London, in Apr 2015, under the supervision of Prof. Francesca Toni. My PhD research is on Reinforcement Learning and Argumentation Theory. More information about me can be found in my personal website: https://sites.google.com/site/yanggaoalex/home

Research Interests

  • Reinforcement Learning (RL), including Deep RL, Inverse RL and Preference-based RL.
  • Interactive NLP
  • Document Summarisation
  • Argumentation Mining
  • Machine Learning in general

Selected Publications

  • Yang Gao, Christian M. Meyer, Iryna Gurevych. APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning. Proceedings of 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018)
  • Wei Wang, Hao Wang, Chen Zhang, Yang Gao. Fredholm Multiple Kernel Learning for Semi-Supervised Domain Adaptation. Proceedings of 31st AAAI Conference on Artificial Intelligence (AAAI 2017)
  • Haijing Liu, Yang Gao, Pin Lv, Mengxue Li, Shiqiang Geng, Minglan Li, Hao Wang. Using Argument-based Features to Predict and Analyse Review Helpfulness. Proceedings of 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017)
  • Yang Gao, Francesca Toni, Hao Wang, Fanjiang Xu. Argumentation based Multi-Agent Decision Making with Privacy Preserved. Proceedings of 15th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016)
  • Yang Gao, Francesca Toni. Potential Based Reward Shaping for Hierarchical Reinforcement Learning. Proceedings of 25th International Joint Conference on Artificial Intelligence (IJCAI 2015)
  • Yang Gao, Francesca Toni. Argumentation Accelerated Reinforcement Learning for Cooperative Multi-Agent Systems. Proceedings of 21st European Conference on Artificial Intelligence (ECAI 2014)
  • Yang Gao, Francesca Toni. Argumentation-Based Reinforcement Learning for RoboCup Soccer Takeaway. Proceedings of 13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014)
  • Yang Gao, Francesca Toni, Robert Craven. Argumentation-Based Reinforcement Learning for RoboCup Soccer Keepaway. Proceedings of 20th European Conference on Artificial Intelligence (ECAI 2012)

Publications

Gruppiere nach: Datum | Typ des Eintrags | Keine Gruppierung
Springe zu: 2018 | 2015
Anzahl der Einträge: 2.

2018

Gao, Yang ; Meyer, Christian M. ; Gurevych, Iryna :
APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning.
[Online-Edition: http://arxiv.org/abs/1808.09658]
In: The 2018 Conference on Empirical Methods in Natural Language Processing, 31.10.2018--04.11.2018, Brussels, Belgium. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
[Konferenz- oder Workshop-Beitrag], (2018)

2015

Gao, Yang ; Toni, Francesca :
Potential Based Reward Shaping for Hierarchical Reinforcement Learning.
[Online-Edition: http://ijcai.org/Abstract/15/493]
In: International Joint Conference on Artificial Intelligence, July 25-31, 2015, Buenos Aires, Argentina. Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2015)
[Konferenz- oder Workshop-Beitrag], (2015)

Diese Liste wurde am Fri Oct 19 06:16:24 2018 CEST generiert.

go to list