ICML 2018 accepted papers on Reinforcement learning
61 of the 623 papers accepted at ICML 2018 (9.8%) are on Reinforcement learning, compared with 5.7% at ICML 2017. They fall into 4 topics.
See ICML 2018 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
Visual and representation RL · 27 papers
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures (571 citations)
- RLlib: Abstractions for Distributed Reinforcement Learning (329 citations)
- Learning by Playing Solving Sparse Reward Tasks from Scratch (255 citations)
- Automatic Goal Generation for Reinforcement Learning Agents (142 citations)
- Synthesizing Programs for Images using Reinforced Adversarial Learning (135 citations)
- Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning (128 citations)
- Programmatically Interpretable Reinforcement Learning (94 citations)
- Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings (79 citations)
- GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms (76 citations)
- Latent Space Policies for Hierarchical Reinforcement Learning (68 citations)
- State Abstractions for Lifelong Reinforcement Learning (67 citations)
- Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control (58 citations)
and 15 more in the interactive map.
Policy gradient and actor-critic · 27 papers
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor (3,754 citations)
- Addressing Function Approximation Error in Actor-Critic Methods (2,316 citations)
- Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator (274 citations)
- Implicit Quantile Networks for Distributional Reinforcement Learning (244 citations)
- Self-Imitation Learning (140 citations)
- Spotlight: Optimizing Device Placement for Training Deep Neural Networks (57 citations)
- The Uncertainty Bellman Equation and Exploration (57 citations)
- Structured Evolution with Compact Architectures for Scalable Policy Optimization (46 citations)
- The Mirage of Action-Dependent Baselines in Reinforcement Learning (43 citations)
- Learning to Explore via Meta-Policy Gradient (41 citations)
- Policy and Value Transfer in Lifelong Reinforcement Learning (39 citations)
- Lipschitz Continuity in Model-based Reinforcement Learning (36 citations)
and 15 more in the interactive map.
MDPs and planning · 5 papers
- Scalable Bilinear Pi Learning Using State and Action Features (28 citations)
- Feedback-Based Tree Search for Reinforcement Learning (8 citations)
- Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning (6 citations)
- Configurable Markov Decision Processes (2 citations)
- Learning the Reward Function for a Misspecified Model
Imitation learning · 2 papers
- Policy Optimization with Demonstrations (78 citations)
- Hierarchical Imitation and Reinforcement Learning (25 citations)
