16 papers · 1 filter
Scalable Causal Imitation Learning
Eylam Tagor, Mingxuan Li, Elias Bareinboim
Imitation learning enables learning a policy in an unknown environment with a latent reward signal using expert demonstrations, but it struggles when the imitator's and expert's ob…
Counterfactual Shapley Credit Assignment
Mingxuan Li, Kai-Zhan Lee, Kaizhan-Lee +1
The Credit Assignment Problem (CAP) is fundamental to developing efficient and explainable Reinforcement Learning (RL) agents. Existing frameworks, whether relying on temporal cont…
Causal Gaussian Processes for Robust Treatment Effect Evaluation with Unobserved Confounding
Junzhe Zhang, Jingyuan Chen, Elias Bareinboim
The presence of confounding bias poses a key challenge in policy evaluation, as the target causal effects of actions are not identifiable (i.e., underdetermined) from observational…
How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings?
Julia Kostin, Kasra Jalaldoust, Elias Bareinboim +2
Machine learning models often degrade when they are deployed on a target distribution that differs from the source distributions they were trained on. Recent work in causality-base…
Adapting, Fast and Slow: On Few-Shot Transportability of Compositions
Kasra Jalaldoust, Elias Bareinboim
Generalization across domains requires stable structure that links the source and target distributions. Building on causal transportability theory, we study a sequential prediction…
Confounding Robust Continuous Control via Automatic Reward Shaping
Mateo Juliani, Mingxuan Li, Elias Bareinboim
Reward shaping has been applied widely to accelerate Reinforcement Learning (RL) agents' training. However, a principled way of designing effective reward shaping functions, especi…