Reinforcement learning in non-stationary environments is challenging due to abrupt and unpredictable changes in dynamics, often causing traditional algorithms to fail to converge. However, in many real-world cases, non-stationarity has some structure that can be exploited to develop algorithms and facilitate theoretical analysis. We introduce one such structure, Switching Non-Stationary Markov Decision Processes (SNS-MDP), where environments switch over time-based on an underlying Markov chain. Under a fixed policy, the value function of an SNS-MDP admits a closed-form solution determined by the Markov chain's statistical properties, and despite the inherent non-stationarity, Temporal Difference (TD) learning methods still converge to the correct value function. Furthermore, policy improvement can be performed, and it is shown that policy iteration converges to the optimal policy. Moreover, since Q-learning converges to the optimal Q-function, it likewise yields the corresponding optimal policy. To illustrate the practical advantages of SNS-MDPs, we present an example in communication networks where channel noise follows a Markovian pattern, demonstrating how this framework can effectively guide decision-making in complex, time-varying contexts.

This paper proposes a robot action planning scheme that provides an efficient and probabilistically safe plan for a robot interacting with an unconcerned human -- someone who is either unaware of the robot's presence or unwilling to engage in ensuring safety. The proposed scheme is predictive, meaning that the robot is required to predict human actions over a finite future horizon; such predictions are often inaccurate in real-world scenarios. One possible approach to reduce the uncertainties is to provide the robot with the capability of reasoning about the human's awareness of potential dangers. This paper discusses that by using a binary variable, so-called danger awareness coefficient, it is possible to differentiate between concerned and unconcerned humans, and provides a learning algorithm to determine this coefficient by observing human actions. Moreover, this paper argues how humans rely on predictions of other agents' future actions (including those of robots in human-robot interaction) in their decision-making. It also shows that ignoring this aspect in predicting human's future actions can significantly degrade the efficiency of the interaction, causing agents to deviate from their optimal paths. The proposed robot action planning scheme is verified and validated via extensive simulation and experimental studies on a LoCoBot WidowX-250.

The growing potential of quadcopters in various domains, such as aerial photography, search and rescue, and infrastructure inspection, underscores the need for real-time control under strict safety and operational constraints. This challenge is compounded by the inherent nonlinear dynamics of quadcopters and the on-board computational limitations they face. This paper aims at addressing these challenges. First, this paper presents a comprehensive procedure for deriving a linear yet efficient model to describe the dynamics of quadrotors, thereby reducing complexity without compromising efficiency. Then, this paper develops a steady-state-aware Model Predictive Control (MPC) to effectively navigate quadcopters, while guaranteeing constraint satisfaction at all times. The main advantage of the steady-state-aware MPC is its low computational complexity, which makes it an appropriate choice for systems with limited computing capacity, like quadcopters. This paper considers Parrot Bebop 2 as the running example, and experimentally validates and evaluates the proposed algorithms.