NeurIPS 2016 accepted papers on Reinforcement learning
22 of the 570 papers accepted at NeurIPS 2016 (3.9%) are on Reinforcement learning. They fall into 4 topics.
See NeurIPS 2016 in the interactive map
Submitting to NeurIPS? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Visual and representation RL · 10 papers
- Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation (822 citations)
- Strategic Attentive Writer for Learning Macro-Actions (80 citations)
- Generating Long-term Trajectories Using Deep Hierarchical Networks (72 citations)
- Adaptive Skills Adaptive Partitions (ASAP) (39 citations)
- Adaptive optimal training of animal behavior (25 citations)
- Catching heuristics are optimal control policies
- Tree-Structured Reinforcement Learning for Sequential Object Localization
- Unifying Count-Based Exploration and Intrinsic Motivation
- Value Iteration Networks
- VIME: Variational Information Maximizing Exploration
Policy gradient and actor-critic · 6 papers
- Deep Exploration via Bootstrapped DQN (451 citations)
- Safe and Efficient Off-Policy Reinforcement Learning (91 citations)
- Learning values across many orders of magnitude (86 citations)
- Guided Policy Search via Approximate Mirror Descent (81 citations)
- Safe Policy Improvement by Minimizing Robust Baseline Regret (64 citations)
- Linear Feature Encoding for Reinforcement Learning (10 citations)
Imitation learning · 3 papers
- Cooperative Inverse Reinforcement Learning (387 citations)
- Generative Adversarial Imitation Learning (353 citations)
- Showing versus doing: Teaching by demonstration (72 citations)
