bandits
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
A lightweight contextual bandit & reinforcement learning library designed to be used in production Python services.
Causal reinforcement learning, organized around Bareinboim's 9-task taxonomy, confounded offline→online RL, POMIS, counterfactual policies, transportability, discovery, imitation, curricula.
Multi-armed Bandit Gymnasium Environment
Python library of bandits and RL agents in different real-world environments
King of the Hill: performant A/B/n testing beyond the basics. Allocation for multi-armed bandits with correlated arms, using the top-k contenders.
Online weight optimization via Thompson Sampling — learns optimal configurations from outcome feedback
A query-aware framework for adaptive hyperparameter optimization of Retrieval-Augmented Generation (RAG) systems using Multi-Armed Bandit methods (UCB1)
