Reinforcement Learning
Discovery of Useful Questions as Auxiliary Tasks
Vivek Veeriah, Matteo Hessel, Zhongwen Xu, Janarthanan Rajendran, Richard L. Lewis, Junhyuk Oh, Hado P. van Hasselt, David Silver, Satinder Singh
Neural Information Processing Systems http://nips.cc/
Model-Based Opponent Modeling Xiaopeng Y u Jiechuan Jiang Wanpeng Zhang Haobin Jiang Zongqing Lu School of Computer Science, Peking University
When one agent interacts with a multi-agent environment, it is challenging to deal with various opponents unseen before.
Oracle Inequalitiesfor Model Selection in Offline Reinforcement Learning
Define = log (M2H / ).
Adaptive Auxiliary Task Weighting for Reinforcement Learning
Xingyu Lin, Harjatin Baweja, George Kantor, David Held
Deep reinforcement learning has enjoyed recent success in domains like games [1, 2], robotic manipulation,andlocomotiontasks[3,4].
ProvableModel-based NonlinearBanditand ReinforcementLearning: ShelveOptimism,Embrace VirtualCurvature
A key algorithmic insight is that optimism may lead to over-exploration even for two-layer neural net model class.
RobustDeepReinforcementLearning throughAdversarialLoss
Our RADIAL-RL agents consistently outperform prior methods when tested against attacks of varying strength and are more computationally efficient to train. In addition, we propose a new evaluation method calledGreedyWorst-Case Reward(GWC) tomeasure attack agnostic robustness of deep RL agents. We show that GWC can be evaluated efficiently and is a good estimate of the reward under the worst possible sequence of adversarial attacks.
Generalized Off-Policy Actor-Critic
Shangtong Zhang, Wendelin Boehmer, Shimon Whiteson
Neural Information Processing Systems http://nips.cc/
