value functions
Functions that estimate the expected rewards of states or actions in reinforcement learning, guiding policy optimization and decision processes.
- Computational Hardness of Reinforcement Learning with Partial $q^{\pi}$-Realizability
- Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning
- Language Models can Self-Improve at State-Value Estimation for Better Search
- Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits
- Real-World Reinforcement Learning of Active Perception Behaviors
- \(\varepsilon\)-Optimally Solving Two-Player Zero-Sum POSGs