Dr. Debabrota B***

Stochastic approximation Bellman Optimality Non-asymptotic convergence bounds Reward machines Q-learning Inter-option learning Intra-option learning Hierarchical reinforcement learning Options Reinforcement Leaning RL Non-asymptotic Convergence Average-reward Algorithmic auditing Sample complexity analysis Active sampling Bias probes Fairness in AI Manipulation proof Efficient Active Auditing Multi-group Fairness Probes Customised preference Instance-dependent regret Minimum empirical divergence Heteroskedastic Bandits Bandits Experimentation Adapting