Learning And Signal Processing
Learning And Signal Processing
Home
People
Publications
Contact
Alberto Bernacchia
Latest
Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
Near-Optimal Sample Complexity in Reward-Free Kernel-based Reinforcement Learning
Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning
Reinforcement Learning Using known Invariances
Cite
×