State-adversarial perturbations—arising from sensor spoofing, environmental interference, or targeted attacks—corrupt observations and invalidate state-wise optimality assumptions commonly made in IRL. We study inverse reinforcement learning (IRL) in state-adversarial MDPs (SA-MDPs) where only perturbed states are observable and propose SAMM-IRL, a max-margin IRL framework that operates purely in the belief (perturbed) space without access to clean states. In contrast to point-wise, state-wise optimality, we adopt a robust optimality notion based on the expected return over the initial-state distribution, which is well-posed under adversarial observation mappings. We prove (i) the existence of robust optimal policies in SA-MDPs, (ii) the contraction properties of intermediate RL operators under fixed and adaptive adversaries, and the iteration bounds for SAMM-IRL max-margin updates in belief space. Empirically, in discrete GridWorld and continuous control, SAMM-IRL achieves stronger reward recovery and imitation performance under adversarial observations than baselines, while maintaining stable policy updates. We further report perturbation parameters and ablation results in the main text to support reproducibility and practical deployment.

In numerous recommender systems, collecting useful information from users is costly, implying that the recommender system has to make active choices by simultaneously learning the observations of the features' states to make useful recommendations to users among available products and services. This paper integrates information acquisition decisions into recommender system. To solve the aforementioned dual learning problem, we propose two different algorithms, namely Sim-OOS and Seq-OOS, where observations are made simultaneously and sequentially, respectively. We prove that both algorithms guarantee a sub linear regret. The developed recommender system can be applied to a variety of real-world applications, including medical informatics, smart transportation, finance, and cyber-security where collecting information before making decisions results in an excessive cost. We validate and evaluate our proposed policies in a medical decision-support system that recommends tests and treatments for breast cancer patients.

In a sequential decision-making problem, having a structural dependency amongst the reward distributions associated with the arms makes it challenging to identify a subset of alternatives that guarantees the optimal collective outcome. Thus, besides individual actions' reward, learning the causal relations is essential to improve the decision-making strategy. To solve the two-fold learning problem described above, we develop the 'combinatorial semi-bandit framework with causally related rewards', where we model the causal relations by a directed graph in a stationary structural equation model. The nodal observation in the graph signal comprises the corresponding base arm's instantaneous reward and an additional term resulting from the causal influences of other base arms' rewards. The objective is to maximize the long-term average payoff, which is a linear function of the base arms' rewards and depends strongly on the network topology. To achieve this objective, we propose a policy that determines the causal relations by learning the network's topology and simultaneously exploits this knowledge to optimize the decision-making process. We establish a sublinear regret bound for the proposed algorithm. Numerical experiments using synthetic and real-world datasets demonstrate the superior performance of our proposed method compared to several benchmarks.