Causal Bandits: Learning Good Interventions via Causal Inference
arXiv:1606.03203
Abstract
We study the problem of using causal models to improve the rate at which good interventions can be learned online in a stochastic environment. Our formalism combines multi-arm bandits and causal inference to model a novel type of bandit feedback that is not exploited by existing approaches. We propose a new algorithm that exploits the causal feedback and prove a bound on its simple regret that is strictly better (in all quantities) than algorithms that do not use the additional causal information.
References in corpus (7)
- Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
- lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits
- Efficient learning by implicit exploration in bandit problems with side observations
- Two Optimal Strategies for Active Learning of Causal Models from Interventional Data
- On the Number of Experiments Sufficient and in the Worst Case Necessary to Identify All Causal Relations Among N Variables
- On Minimax Optimal Offline Policy Evaluation
- Decoupling Exploration and Exploitation in Multi-Armed Bandits
Cited by in corpus (15)
- Beyond Ads: Sequential Decision-Making Algorithms in Law and Public Policy
- Identifying Best Interventions through Online Importance Sampling
- Playing against Nature: causal discovery for decision making under uncertainty
- Causal Bandits with Unknown Graph Structure
- Regret Analysis of Bandit Problems with Causal Background Knowledge
- Bandit Algorithms for Precision Medicine
- Combining Offline Causal Inference and Online Bandit Learning for Data Driven Decision
- Contextual Bandits with Stochastic Experts
- Balanced Linear Contextual Bandits
- Causal Structure Learning: a Bayesian approach based on random graphs
- Rarely-switching linear bandits: optimization of causal effects for the real world
- Causal Simulations for Uplift Modeling
- Instrument-Armed Bandits
- Intervention Efficient Algorithm for Two-Stage Causal MDPs
- Causal Games and Causal Nash Equilibrium