exploration-exploitation balance
The exploration-exploitation balance is a fundamental concept in reinforcement learning that deals with the trade-off between exploring new actions to gather more information and exploiting known actions that yield high rewards.
- A Bayesian Fast-Slow Framework to Mitigate Interference in Non-Stationary Reinforcement Learning
- A Reinforcement Learning-based Bidding Strategy for Data Consumers in Auction-based Federated Learning
- Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMs
- Graph-based Symbolic Regression with Invariance and Constraint Encoding
- Improving Monte Carlo Tree Search for Symbolic Regression
- Online Feedback Efficient Active Target Discovery in Partially Observable Environments
- Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning
- PlanU: Large Language Model Reasoning through Planning under Uncertainty
- Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction