conftrace_

exploration-exploitation balance

3 papers

Explore in graph

Co-occurring keywords

strategic replication (1) hierarchical ucb (1) dialogue policy (60) elite individual injection (1) evolutionary algorithm (264) surrogate model (181) acquisition function (129) regret bound (1926) multi-armed bandit (1098) bayesian optimization (624)

Papers

An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals ACL 2025
Self-Adjusting Weighted Expected Improvement for Bayesian Optimization AUTOML 2023
Multi-armed Bandit Algorithm against Strategic Replication AISTATS 2022