AAAI 2022 accepted papers on Reinforcement learning
78 of the 1,319 papers accepted at AAAI 2022 (5.9%) are on Reinforcement learning, compared with 5.2% at AAAI 2021. They fall into 5 topics.
See AAAI 2022 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 · 30 papers
- Fully Adaptive Framework: Neural Computerized Adaptive Testing for Online Education (60 citations)
- CADRE: A Cascade Deep Reinforcement Learning Framework for Vision-Based Autonomous Urban Driving (38 citations)
- OAM: An Option-Action Reinforcement Learning Framework for Universal Multi-Intersection Control (35 citations)
- Multi-Sacle Dynamic Coding Improved Spiking Actor Network for Reinforcement Learning (34 citations)
- Adapt to Environment Sudden Changes by Learning a Context Sensitive Policy (28 citations)
- Constrained Prescriptive Trees via Column Generation (28 citations)
- Creativity of AI: Automatic Symbolic Option Discovery for Facilitating Deep Reinforcement Learning (23 citations)
- EMVLight: A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles (22 citations)
- Robust Adversarial Reinforcement Learning with Dissipation Inequation Constraint (20 citations)
- Introducing Symmetries to Black Box Meta Reinforcement Learning (16 citations)
- Reinforcement Learning with Stochastic Reward Machines (16 citations)
- Discovering State and Action Abstractions for Generalized Task and Motion Planning (14 citations)
and 18 more in the interactive map.
Policy gradient and actor-critic · 26 papers
- Efficient Continuous Control with Double Actors and Regularized Critics (58 citations)
- Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms (38 citations)
- Exploring Safer Behaviors for Deep Reinforcement Learning (27 citations)
- Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic (20 citations)
- Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning (19 citations)
- Stochastic Planner-Actor-Critic for Unsupervised Deformable Image Registration (13 citations)
- Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization (11 citations)
- What about Inputting Policy in Value Function: Policy Representation and Policy-Extended Value Function Approximator (10 citations)
- Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation (8 citations)
- Controlling Underestimation Bias in Reinforcement Learning via Quasi-median Operation (8 citations)
- An Efficient Combinatorial Optimization Model Using Learning-to-Rank Distillation (7 citations)
- Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization (7 citations)
and 14 more in the interactive map.
MDPs and planning · 12 papers
- Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach (23 citations)
- A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision Processes (11 citations)
- Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes (5 citations)
- Learning Probably Approximately Complete and Safe Action Models for Stochastic Worlds (5 citations)
- Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability (5 citations)
- Sample-Efficient Iterative Lower Bound Optimization of Deep Reactive Policies for Planning in Continuous MDPs (5 citations)
- Blockwise Sequential Model Learning for Partially Observable Reinforcement Learning (4 citations)
- Planning with Participation Constraints (4 citations)
- Policy Learning for Robust Markov Decision Process with a Mismatched Generative Model (4 citations)
- Globally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes (3 citations)
- Structure Learning-Based Task Decomposition for Reinforcement Learning in Non-stationary Environments (2 citations)
- Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods (2 citations)
Offline RL · 6 papers
- DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning (62 citations)
- Constraints Penalized Q-learning for Safe Offline Reinforcement Learning (51 citations)
- Offline Reinforcement Learning as Anti-exploration (22 citations)
- Text-Based Interactive Recommendation via Offline Reinforcement Learning (9 citations)
- State Deviation Correction for Offline Reinforcement Learning (8 citations)
- Towards Off-Policy Learning for Ranking Policies with Logged Feedback (7 citations)
Imitation learning · 4 papers
- Self-Adaptive Imitation Learning: Learning Tasks with Delayed Rewards from Sub-optimal Demonstrations (11 citations)
- Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency (8 citations)
- Programmatic Reward Design by Example (8 citations)
- Stage Conscious Attention Network (SCAN): A Demonstration-Conditioned Policy for Few-Shot Imitation (1 citation)
