Counterfactual Data-Fusion for Online Reinforcement Learners
The Multi-Armed Bandit problem with Unobserved Confounders (MABUC) considers decision-making settings where unmeasured variables can influence both the agent’s decisions and received rewards (Bareinboim et al., 2015). Recent findings showed that unobserved confounders (UCs) pose a unique challenge to algorithms based on standard randomization (i.e., experimental data); if UCs are naively averaged out, these algorithms behave sub-optimally, possibly incurring infinite regret. In this paper, we show how counterfactual-based decision-making circumvents these problems and leads to a coherent fusion of observational and experimental data. We then demonstrate this new strategy in an enhanced Thompson Sampling bandit player, and support our findings’ efficacy with extensive simulations.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualDecision MakingThompson SamplingSimilar Papers 제목 키워드 기반
An effect analysis of the balancing techniques on the counterfactual explanations of student success prediction models
In the past decade, we have experienced a massive boom in the usage of digital solutions in higher education. Due to this boom, large amounts of data have enabled advanced data analysis methods to support learners and ex…
counterfactualOffline Learning of Counterfactual Predictions for Real-World Robotic Reinforcement Learning
We consider real-world reinforcement learning (RL) of robotic manipulation tasks that involve both visuomotor skills and contact-rich skills. We aim to train a policy that maps multimodal sensory observations (vision and…
counterfactualreinforcement-learningReinforcement LearningReinforcement Learning (RL)Don't Explain Noise: Robust Counterfactuals for Randomized Ensembles
Counterfactual explanations describe how to modify a feature vector in order to flip the outcome of a trained classifier. Obtaining robust counterfactual explanations is essential to provide valid algorithmic recourse an…
counterfactualvalidCollaborative Evolutionary Reinforcement Learning
Deep reinforcement learning algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically struggle with achieving effective exploration and are extremely sensitive to…
continuous-controlContinuous ControlDeep Reinforcement LearningMuJoCo+3Assessing the Impact of Upselling in Online Fantasy Sports
This study explores the impact of upselling on user engagement. We model users' deposit behaviour on the fantasy sports platform Dream11. Subsequently, we develop an experimental framework to evaluate the effect of upsel…
counterfactual