offline reinforcement learning
A branch of reinforcement learning that deals with learning optimal policies from previously collected experience without interacting with the environment. It allows for the reuse of past data to improve model training.
- A Clean Slate for Offline Reinforcement Learning
- A Clean Slate for Offline Reinforcement Learning
- ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
- Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning
- BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces
- FANS: A Flatness-Aware Network Structure for Generalization in Offline Reinforcement Learning
- Finite-Time Bounds for Average-Reward Fitted Q-Iteration
- Forecasting in Offline Reinforcement Learning for Non-stationary Environments
- Horizon Reduction Makes RL Scalable
- Less is More: an Attention-free Sequence Prediction Modeling for Offline Embodied Learning
- Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol
- Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies
- Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
- Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL
- Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning
- Prior-Guided Diffusion Planning for Offline Reinforcement Learning
- Prompt Tuning Decision Transformers with Structured and Scalable Bandits
- Rebalancing Return Coverage for Conditional Sequence Modeling in Offline Reinforcement Learning
- Scaling Offline RL via Efficient and Expressive Shortcut Models
- Structural Information-based Hierarchical Diffusion for Offline Reinforcement Learning