ICML 2016 accepted papers on Reinforcement learning
17 of the 322 papers accepted at ICML 2016 (5.3%) are on Reinforcement learning. They fall into 3 topics.
See ICML 2016 in the interactive map
Submitting to ICML? 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
Policy gradient and actor-critic · 10 papers
- Dueling Network Architectures for Deep Reinforcement Learning (1,777 citations)
- Asynchronous Methods for Deep Reinforcement Learning (1,685 citations)
- Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization (591 citations)
- Continuous Deep Q-Learning with Model-based Acceleration (320 citations)
- Generalization and Exploration via Randomized Value Functions (80 citations)
- Doubly Robust Off-policy Value Evaluation for Reinforcement Learning (79 citations)
- Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning (73 citations)
- Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control (56 citations)
- Softened Approximate Policy Iteration for Markov Games (26 citations)
- Model-Free Trajectory Optimization for Reinforcement Learning (18 citations)
Visual and representation RL · 5 papers
- Benchmarking Deep Reinforcement Learning for Continuous Control (949 citations)
- Control of Memory, Active Perception, and Action in Minecraft (164 citations)
- Near Optimal Behavior via Approximate State Abstraction (111 citations)
- Graying the black box: Understanding DQNs (56 citations)
- Hierarchical Decision Making In Electricity Grid Management (26 citations)
Imitation learning · 2 papers
- Model-Free Imitation Learning with Policy Optimization (41 citations)
- Smooth Imitation Learning for Online Sequence Prediction (14 citations)
