Skip to yearly menu bar Skip to main content


Search All 2019 Events
 

14 Results

<<   <   Page 1 of 2   >   >>
Oral
Wed 8:30 FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models
Will Grathwohl · Tian Qi Chen · Jesse Bettencourt · Ilya Sutskever · David Duvenaud
Poster
Wed 9:00 Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization
Takayuki Osa · Voot Tangkaratt · Masashi Sugiyama
Poster
Thu 9:00 Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs
Sachin Kumar · Yulia Tsvetkov
Poster
Wed 9:00 Information asymmetry in KL-regularized RL
Alexandre Galashov · Siddhant Jayakumar · Leonard Hasenclever · Dhruva Tirumala · Jonathan Schwarz · Guillaume Desjardins · Wojciech M Czarnecki · Yee Whye Teh · Razvan Pascanu · Nicolas Heess
Poster
Tue 14:30 Stochastic Optimization of Sorting Networks via Continuous Relaxations
Aditya Grover · Eric J. Wang · Aaron Zweig · Stefano Ermon
Poster
Wed 9:00 Selfless Sequential Learning
Rahaf Aljundi · Marcus Rohrbach · Tinne Tuytelaars
Poster
Wed 9:00 Overcoming Catastrophic Forgetting for Continual Learning via Model Adaptation
Wenpeng Hu · Zhou Lin · Bing Liu · Chongyang Tao · Jay Tao · Jinwen Ma · Dongyan Zhao · Rui Yan
Poster
Wed 9:00 Composing Complex Skills by Learning Transition Policies
Youngwoon Lee · Shao-Hua Sun · Sriram Somasundaram · Edward S Hu · Joseph Lim
Poster
Wed 9:00 FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models
Will Grathwohl · Tian Qi Chen · Jesse Bettencourt · Ilya Sutskever · David Duvenaud
Poster
Wed 9:00 Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks
Amanpreet Singh · Tushar Jain · Sainbayar Sukhbaatar
Poster
Wed 9:00 Efficient Lifelong Learning with A-GEM
Arslan Chaudhry · Marc'Aurelio Ranzato · Marcus Rohrbach · Mohamed Elhoseiny
Poster
Wed 9:00 Neural Probabilistic Motor Primitives for Humanoid Control
Josh Merel · Leonard Hasenclever · Alexandre Galashov · Arun Ahuja · Vu Pham · Greg Wayne · Yee Whye Teh · Nicolas Heess