Reinforcement Learning
Inference Aided Reinforcement Learning for Incentive Mechanism Design in Crowdsourcing
Zehong Hu, Yitao Liang, Jie Zhang, Zhao Li, Yang Liu
We theoretically prove that RIL is able to incentivize rational workers to provide high-quality labels.
Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion
Jacob Buckman, Danijar Hafner, George Tucker, Eugene Brevdo, Honglak Lee
We propose stochastic ensemble value expansion (STEVE), a novel model-based technique that addresses this issue. By dynamically interpolating between model rollouts of various horizon lengths for each individual example, STEVE ensures that the model is only utilized when doing so does not introduce significant errors.
Data-Efficient Hierarchical Reinforcement Learning
Ofir Nachum, Shixiang (Shane) Gu, Honglak Lee, Sergey Levine
Neural Information Processing Systems http://nips.cc/
Joint Active Feature Acquisition and Classification with Variable-Size Set Encoding
Hajin Shim, Sung Ju Hwang, Eunho Yang
Neural Information Processing Systems http://nips.cc/
Learning to Navigate in Cities Without a Map
Piotr Mirowski, Matt Grimes, Mateusz Malinowski, Karl Moritz Hermann, Keith Anderson, Denis Teplyashin, Karen Simonyan, koray kavukcuoglu, Andrew Zisserman, Raia Hadsell
The majority of algorithms involve building an explicit map during an exploration phase and then planning and acting via that representation. In this work, we are interested in pushing the limits of end-to-end deep reinforcement learning for navigation by proposing new methods and demonstrating their performance in large-scale, real-world environments.
Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning
Neural Information Processing Systems http://nips.cc/
Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation
Qiang Liu, Lihong Li, Ziyang Tang, Dengyong Zhou
In this paper, we propose a new off-policy estimator that applies IS directly on the stationary state-visitation distributions to avoid the exploding variance faced by existing methods.
Occam's razor is insufficient to infer the preferences of irrational agents
Stuart Armstrong, Sรถren Mindermann
In today's reinforcement learning systems, a simple reward function is often hand-crafted, and still
Exploration in Structured Reinforcement Learning
Jungseul Ok, Alexandre Proutiere, Damianos Tranos
Neural Information Processing Systems http://nips.cc/
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
Jiaxuan You, Bowen Liu, Zhitao Ying, Vijay Pande, Jure Leskovec
Generating novel graph structures that optimize given objectives while obeying some given underlying rules is fundamental for chemistry, biology and social science research.