Learning from First Discrepancies with Joint Reset and Pilot Guarantees
cs.LG
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
- PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning
- Sustained Space Complexity
- Scalable Online Exploration via Coverability
- On Learning Verifiers and Implications to Chain-of-Thought Reasoning
- Agnostic Smoothed Online Learning without Knowledge of the Base Measure
- On Explicit Constructions of Extremely Depth Robust Graphs
- Efficient Optimal Learning for Contextual Bandits
- Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift
- When is Agnostic Reinforcement Learning Statistically Tractable?
- Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning
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