ANCHOR: KL-Anchored Adaptation for Stable Offline-to-Online RL
cs.LG, cs.AI
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/Cho-Geonwoo/ANCHOR
Project page: https://agarwl.github.io/rliable
Terminology
Sources
- Layer Normalization
- Improving TD3-BC: Relaxed Policy Constraint for Offline Learning and Stable Online Fine-Tuning
- Exploration by Random Network Distillation
- Randomized Ensembled Double Q-Learning: Learning Fast Without a Model
- D4RL: Datasets for Deep Data-Driven Reinforcement Learning
- Extreme Q-Learning: MaxEnt RL without Entropy
- A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning
- Imitation Bootstrapped Reinforcement Learning
- A Survey of the Self Supervised Learning Mechanisms for Vision Transformers
- Adam: A Method for Stochastic Optimization
- PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning
- AWAC: Accelerating Online Reinforcement Learning with Offline Datasets
- OGBench: Benchmarking Offline Goal-Conditioned RL
- Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
- Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations
- Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only
- Policy Expansion for Bridging Offline-to-Online Reinforcement Learning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- 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