function approximation
Function approximation refers to the process of estimating an unknown function based on known inputs and outputs, a fundamental task in machine learning to model complex mappings.
- Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL
- Finite-Time Bounds for Average-Reward Fitted Q-Iteration
- From Kolmogorov to Cauchy: Shallow XNet Surpasses KANs
- Learning Theory for Kernel Bilevel Optimization
- Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
- Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach
- Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback
- Reward-Aware Proto-Representations in Reinforcement Learning
- Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding