AAAI 2017 accepted papers on Reinforcement learning
27 of the 639 papers accepted at AAAI 2017 (4.2%) are on Reinforcement learning, compared with 5.1% at AAAI 2016. They fall into 4 topics.
See AAAI 2017 in the interactive map
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 · 9 papers
- Query-Efficient Imitation Learning for End-to-End Simulated Driving (304 citations)
- Knowledge Transfer for Deep Reinforcement Learning with Hierarchical Experience Replay (119 citations)
- Landmark-Based Heuristics for Goal Recognition (84 citations)
- Grounded Action Transformation for Robot Learning in Simulation (81 citations)
- Automatic Curriculum Graph Generation for Reinforcement Learning Agents (70 citations)
- Self-Correcting Models for Model-Based Reinforcement Learning (47 citations)
- Where to Add Actions in Human-in-the-Loop Reinforcement Learning (41 citations)
- An Efficient Approach to Model-Based Hierarchical Reinforcement Learning (21 citations)
- Extracting Urban Microclimates from Electricity Bills (3 citations)
Policy gradient and actor-critic · 9 papers
- The Option-Critic Architecture (784 citations)
- Transfer Reinforcement Learning with Shared Dynamics (66 citations)
- Sequential Classification-Based Optimization for Direct Policy Search (56 citations)
- OFFER: Off-Environment Reinforcement Learning (28 citations)
- Accelerated Gradient Temporal Difference Learning (23 citations)
- Estimating the Maximum Expected Value in Continuous Reinforcement Learning Problems (19 citations)
- Scalable Multitask Policy Gradient Reinforcement Learning (16 citations)
- Importance Sampling with Unequal Support (10 citations)
- Policy Search with High-Dimensional Context Variables (6 citations)
MDPs and planning · 7 papers
- Accelerated Vector Pruning for Optimal POMDP Solvers (39 citations)
- Dynamically Constructed (PO)MDPs for Adaptive Robot Planning (25 citations)
- Optimizing Quantiles in Preference-Based Markov Decision Processes (14 citations)
- Hindsight Optimization for Hybrid State and Action MDPs (13 citations)
- Optimizing Expectation with Guarantees in POMDPs (12 citations)
- Collective Multiagent Sequential Decision Making Under Uncertainty
- Decentralized Planning in Stochastic Environments with Submodular Rewards
