We present recent advances and statistical developments for evaluating Dynamic Treatment Regimes (DTR), which allow the treatment to be dynamically tailored according to evolving subject-level data. Identification of an optimal DTR is a key component for precision medicine and personalized health care. We develop a tree-based doubly robust reinforcement learning (T-RL) method, and a new Stochastic-Tree Search method, ST-RL, for evaluating optimal DTRs, which contributes to the existing literature in its non-greedy policy search and demonstrates outstanding performances. We further develop a Restricted Tree-based Reinforcement Learning (RT-RL) method that searches for an interpretable DTR to maximize the expected outcome, given a (set of) user-specified restriction(s), which specifies treatment options that ought not to be considered as part of the estimated tree-based DTR. The method is illustrated using an observational dataset to estimate a two-stage stepped-up DTR for guiding the level of care placement for adolescents with substance use disorder.