Reinforcement Learning
LearningRewardMachinesforPartially ObservableReinforcementLearning
RL agents learn policies from experience.
Planning in entropy-regularized Markov decision processes and games
Jean-Bastien Grill, Omar Darwiche Domingues, Pierre Menard, Remi Munos, Michal Valko
Neural Information Processing Systems http://nips.cc/
Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling
Tengyang Xie, Yifei Ma, Yu-Xiang Wang
Solving OPE is often the starting point in many RL applications. To tackle the problem of OPE, the idea of importance sampling (IS) corrects the mismatch in the distributions under the behavior policy and target policy.
VRL3: AData-DrivenFrameworkforVisualDeep ReinforcementLearning
Our framework has three stages: instage 1,we leverage non-RL datasets (e.g. ImageNet) to learn task-agnostic visual representations; in stage 2, we use offline RL data (e.g. a limited number of expert demonstrations) to convert the task-agnostic representations intomorepowerfultask-specific representations; in stage 3, we fine-tune the agent with online RL.
DAC: The Double Actor-Critic Architecture for Learning Options
Shangtong Zhang, Shimon Whiteson
Neural Information Processing Systems http://nips.cc/
58a799d16fb0c1f2014e98f4ba972b25-Paper-Conference.pdf
RL that utilize function approximation to generalize observational data to unknown states/actions. The goal of this paper is to study the sample complexity of policy-based RL, which is arguably the simplest setting for RL with function approximation (Kearns et al., 1999; Kakade, 2003).
Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies
Sungryull Sohn, Junhyuk Oh, Honglak Lee
Neural Information Processing Systems http://nips.cc/