AAAI 2024 accepted papers on Reinforcement learning
137 of the 2,864 papers accepted at AAAI 2024 (4.8%) are on Reinforcement learning, compared with 5.6% at AAAI 2023. They fall into 6 topics.
See AAAI 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Visual and representation RL · 52 papers
- Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning (41 citations)
- EarnHFT: Efficient Hierarchical Reinforcement Learning for High Frequency Trading (21 citations)
- π-Light: Programmatic Interpretable Reinforcement Learning for Resource-Limited Traffic Signal Control (18 citations)
- Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations (12 citations)
- Cheaper and Faster: Distributed Deep Reinforcement Learning with Serverless Computing (10 citations)
- What Effects the Generalization in Visual Reinforcement Learning: Policy Consistency with Truncated Return Prediction (9 citations)
- A Transfer Approach Using Graph Neural Networks in Deep Reinforcement Learning (8 citations)
- Graph-Based Prediction and Planning Policy Network (GP3Net) for Scalable Self-Driving in Dynamic Environments Using Deep Reinforcement Learning (8 citations)
- ACAMDA: Improving Data Efficiency in Reinforcement Learning through Guided Counterfactual Data Augmentation (7 citations)
- BertRLFuzzer: A BERT and Reinforcement Learning Based Fuzzer (Student Abstract) (7 citations)
- Improving Autonomous Separation Assurance through Distributed Reinforcement Learning with Attention Networks (7 citations)
- Meta-Reinforcement Learning via Exploratory Task Clustering (7 citations)
and 40 more in the interactive map.
Policy gradient and actor-critic · 38 papers
- Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation (12 citations)
- Fractional Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing (10 citations)
- Two-Stage Evolutionary Reinforcement Learning for Enhancing Exploration and Exploitation (9 citations)
- A Reinforcement-Learning-Based Multiple-Column Selection Strategy for Column Generation (7 citations)
- MetaRLEC: Meta-Reinforcement Learning for Discovery of Brain Effective Connectivity (7 citations)
- OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments (7 citations)
- Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration (7 citations)
- Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling (6 citations)
- ERL-TD: Evolutionary Reinforcement Learning Enhanced with Truncated Variance and Distillation Mutation (6 citations)
- Towards Safe Policy Learning under Partial Identifiability: A Causal Approach (6 citations)
- Deep Reinforcement Learning for Early Diagnosis of Lung Cancer (5 citations)
- Enhancing Off-Policy Constrained Reinforcement Learning through Adaptive Ensemble C Estimation (5 citations)
and 26 more in the interactive map.
Offline RL · 19 papers
- A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning (19 citations)
- Critic-Guided Decision Transformer for Offline Reinforcement Learning (19 citations)
- ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning (12 citations)
- Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning (7 citations)
- Stitching Sub-trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL (7 citations)
- NondBREM: Nondeterministic Offline Reinforcement Learning for Large-Scale Order Dispatching (6 citations)
- Offline Model-Based Optimization via Policy-Guided Gradient Search (6 citations)
- Online Reinforcement Learning-Based Pedagogical Planning for Narrative-Centered Learning Environments (6 citations)
- An Implicit Trust Region Approach to Behavior Regularized Offline Reinforcement Learning (5 citations)
- OCEAN-MBRL: Offline Conservative Exploration for Model-Based Offline Reinforcement Learning (4 citations)
- SUF: Stabilized Unconstrained Fine-Tuning for Offline-to-Online Reinforcement Learning (4 citations)
- CUDC: A Curiosity-Driven Unsupervised Data Collection Method with Adaptive Temporal Distances for Offline Reinforcement Learning (3 citations)
and 7 more in the interactive map.
MDPs and planning · 12 papers
- Principal-Agent Reward Shaping in MDPs (5 citations)
- Long-Term Safe Reinforcement Learning with Binary Feedback (4 citations)
- A PAC Learning Algorithm for LTL and Omega-Regular Objectives in MDPs (3 citations)
- Stop! Planner Time: Metareasoning for Probabilistic Planning Using Learned Performance Profiles (3 citations)
- Personalized Reinforcement Learning with a Budget of Policies (2 citations)
- Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge (2 citations)
- Solving Non-rectangular Reward-Robust MDPs via Frequency Regularization (2 citations)
- A Surprisingly Simple Continuous-Action POMDP Solver: Lazy Cross-Entropy Search Over Policy Trees (1 citation)
- Omega-Regular Decision Processes (1 citation)
- Optimizing Local Satisfaction of Long-Run Average Objectives in Markov Decision Processes (1 citation)
- Relative Policy-Transition Optimization for Fast Policy Transfer (1 citation)
- Sketched Newton Value Iteration for Large-Scale Markov Decision Processes (1 citation)
Imitation learning · 11 papers
- No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning (13 citations)
- Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective (12 citations)
- RLfOLD: Reinforcement Learning from Online Demonstrations in Urban Autonomous Driving (12 citations)
- DiffAIL: Diffusion Adversarial Imitation Learning (10 citations)
- Harnessing Network Effect for Fake News Mitigation: Selecting Debunkers via Self-Imitation Learning (6 citations)
- Meta-Inverse Reinforcement Learning for Mean Field Games via Probabilistic Context Variables (5 citations)
- GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimation (4 citations)
- Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning (3 citations)
- Recent Advancements in Inverse Reinforcement Learning (2 citations)
- Robust Visual Imitation Learning with Inverse Dynamics Representations (2 citations)
- Making AI Policies Transparent to Humans through Demonstrations (1 citation)
RL from feedback · 5 papers
- Towards Automated RISC-V Microarchitecture Design with Reinforcement Learning (13 citations)
- Rating-Based Reinforcement Learning (11 citations)
- Learning Optimal Advantage from Preferences and Mistaking It for Reward (5 citations)
- Can You Rely on Synthetic Labellers in Preference-Based Reinforcement Learning? It’s Complicated (3 citations)
- ESRL: Efficient Sampling-Based Reinforcement Learning for Sequence Generation (3 citations)