AAAI 2016 accepted papers on Reinforcement learning
28 of the 548 papers accepted at AAAI 2016 (5.1%) are on Reinforcement learning. They fall into 6 topics.
See AAAI 2016 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
MDPs and planning · 15 papers
- Reinforcement Learning with Parameterized Actions (195 citations)
- RAO*: An Algorithm for Chance-Constrained POMDP's (70 citations)
- A Symbolic SAT-Based Algorithm for Almost-Sure Reachability with Small Strategies in POMDPs (39 citations)
- Generalized Emphatic Temporal Difference Learning: Bias-Variance Analysis (33 citations)
- Learning for Decentralized Control of Multiagent Systems in Large, Partially-Observable Stochastic Environments (30 citations)
- Efficient Average Reward Reinforcement Learning Using Constant Shifting Values (25 citations)
- Exploiting Anonymity in Approximate Linear Programming: Scaling to Large Multiagent MDPs (23 citations)
- Compressed Conditional Mean Embeddings for Model-Based Reinforcement Learning (17 citations)
- Solving Risk-Sensitive POMDPs With and Without Cost Observations (17 citations)
- Efficient PAC-Optimal Exploration in Concurrent, Continuous State MDPs with Delayed Updates (16 citations)
- Target Surveillance in Adversarial Environments Using POMDPs (14 citations)
- Incremental Stochastic Factorization for Online Reinforcement Learning (9 citations)
and 3 more in the interactive map.
Visual and representation RL · 7 papers
- Efficient Macroscopic Urban Traffic Models for Reducing Congestion: A PDDL+ Planning Approach (86 citations)
- Reuse of Neural Modules for General Video Game Playing (23 citations)
- Collective Noise Contrastive Estimation for Policy Transfer Learning (14 citations)
- Sparse Latent Space Policy Search (9 citations)
- Implementing Troubleshooting with Batch Repair (7 citations)
- Big-Data Mechanisms and Energy-Policy Design (3 citations)
- Energy- and Cost-Efficient Pumping Station Control (3 citations)
Policy gradient and actor-critic · 2 papers
- Deep Reinforcement Learning with Double Q-Learning (6,796 citations)
- Increasing the Action Gap: New Operators for Reinforcement Learning (124 citations)
Imitation learning · 2 papers
RL from feedback · 1 paper
- Model-Free Preference-Based Reinforcement Learning (70 citations)
