| Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL | May 28, 2024 | Offline RLReinforcement Learning (RL) | CodeCode Available | 1 |
| AlignIQL: Policy Alignment in Implicit Q-Learning through Constrained Optimization | May 28, 2024 | D4RLOffline RL | CodeCode Available | 0 |
| Unified Preference Optimization: Language Model Alignment Beyond the Preference Frontier | May 28, 2024 | Language ModelingLanguage Modelling | —Unverified | 0 |
| OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators | May 27, 2024 | Decision MakingOffline RL | —Unverified | 0 |
| Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear q^π-Realizability and Concentrability | May 27, 2024 | Computational EfficiencyOffline RL | —Unverified | 0 |
| Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning | May 27, 2024 | Gym halfcheetah-mediumGym halfcheetah-medium-expert | CodeCode Available | 2 |
| Q-value Regularized Transformer for Offline Reinforcement Learning | May 27, 2024 | D4RLOffline RL | CodeCode Available | 1 |
| GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning | May 27, 2024 | Data AugmentationDecision Making | CodeCode Available | 1 |
| Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization | May 25, 2024 | continuous-controlContinuous Control | CodeCode Available | 2 |
| Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search | May 24, 2024 | Code GenerationLanguage Modelling | CodeCode Available | 1 |
