Informed Posterior Sampling: More Efficient Online Learning with Few Offline Demonstrations in Average-Reward MDPs
cs.LG, cs.AI, cs.SY, eess.SY, stat.ML
Submitted: 2023-10-17
Updated: 2026-11-09
Terminology
Sources
- Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity
- Model-Based Offline Planning
- Efficient Online Reinforcement Learning with Offline Data
- Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space
- Finetuning Offline World Models in the Real World
- MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
- Leveraging Demonstrations to Improve Online Learning: Quality Matters
- Training Compute-Optimal Large Language Models
- Imitation Bootstrapped Reinforcement Learning
- Offline Reinforcement Learning with Implicit Q-Learning
- When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?
- Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
- AWAC: Accelerating Online Reinforcement Learning with Offline Datasets
- Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient
- LaMDA: Language Models for Dialog Applications
- Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage
- Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
- Leveraging Offline Data in Online Reinforcement Learning
- Safe Exploration for Efficient Policy Evaluation and Comparison
- Adaptive Policy Learning for Offline-to-Online Reinforcement Learning
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning