<div>As the manufacturing and healthcare systems becomes more complex, efficiently managing these systems requires cooperation and coordination between different parties. This dissertation examines the coordination issues in a supply chain problem and diagnostic decision making in the healthcare system. Below, we provide a brief description of the problem and results achieved. </div><div> </div><div>With supply chain becoming increasingly extended, the uncertainty in the upstream production process can greatly affect the material flow that aims toward meeting the uncertain demand at the downstream. In Chapter 2, we analyze a two-location system in which the upstream production facility experiences random capacities and the downstream store faces random demands. Instead of decomposing the profit function widely used to treat multi-echelon systems, our approach builds on the notions of stochastic functions, in particular, the stochastic linearity in midpoint and the directional concavity in midpoint, which establishes the concavity and submodularity of the profit functions. In general, it is optimal to follow a two-level state-dependent threshold policy such that an order is issued at a location if and only if the inventory position of that location is below the corresponding threshold. When the salvage values of the ending inventories are linear, the profit function becomes decomposable in the inventory positions at different locations and the optimal threshold policy reduces to the echelon base-stock policy. The effect of production and demand uncertainty on inventory levels depends critically on whether the production capacity is limited or ample in relation to the demand. Only when the capacity is about the demand, the upstream facility holds positive inventory; otherwise, all units produced are immediately shipped to the downstream. We further extend our analysis to situations with general stochastic production functions and with multiple locations.</div><div> </div><div> </div><div>In Chapter 3, we examine the two-stage supply chain problem (described in Chapter 2) under the decentralized control. We consider two scenarios. In the first scenario, the retail store does not have any supply information including the inventory level at the manufacturing facility. We show that the upstream and downstream can be dynamically coordinated with proper transfer payment defined on local inventories and their own value function in the dynamic recursion. In the second scenario, the demand distribution is unknown to the manufacturing facility as well as the retail store does not know the supply information. We characterize the optimal transfer contracts under which coordination can be achieved, and propose an iterative algorithm to compute the optimal transfer contracts in the decentralized setting. The total profit of the decentralized system under our algorithm is guaranteed to converge to the centralized optimal channel profit for any demand and supply distribution functions. </div><div> </div><div>In Chapter 4, we provide a case study for the framework developed in [1]. The authors study the evaluation and integration of new medical research considering the operational impacts. As a case study, we first describe their two-station queueing control model using the MDP framework. We then present the structural properties of the MDP model. Since multiple classes of patients are considered in the MDP model, it becomes challenging to solve when the the number of patient classes increases. We describe an efficient heuristic algorithm developed by [1] to overcome the curse of dimensionality. We also test the numerical performance of their heuristic algorithm, and find that the largest optimality gap is less than 1.50% among all the experiments. </div><div> </div>

Classical value estimation reinforcement learning algorithms do not perform very well in dynamic environments. On the other hand, the reinforcement learning of animals is quite flexible: they can adapt to dynamic environments very quickly and deal with noisy inputs very effectively. One feature that may contribute to animals' good performance in dynamic environments is that they learn and perceive the time to reward. In this research, we attempt to learn and perceive the time to reward and explore situations where the learned time information can be used to improve the performance of the learning agent in dynamic environments. The type of dynamic environments that we are interested in is that type of switching environment which stays the same for a long time, then changes abruptly, and then holds for a long time before another change. The type of dynamics that we mainly focus on is the time to reward, though we also extend the ideas to learning and perceiving other criteria of optimality, e.g. the discounted return, so that they can still work even when the amount of reward may also change. Specifically, both the mean and variance of the time to reward are learned and then used to detect changes in the environment and to decide whether the agent should give up a suboptimal action. When a change in the environment is detected, the learning agent responds specifically to the change in order to recover quickly from it. When it is found that the current action is still worse than the optimal one, the agent gives up this time's exploration of the action and then remakes its decision in order to avoid longer than necessary exploration. The results of our experiments using two real-world problems show that they have effectively sped up learning, reduced the time taken to recover from environmental changes, and improved the performance of the agent after the learning converges in most of the test cases compared with classical value estimation reinforcement learning algorithms. In addition, we have successfully used spiking neurons to implement various phenomena of classical conditioning, the simplest form of animal reinforcement learning in dynamic environments, and also pointed out a possible implementation of instrumental conditioning and general reinforcement learning using similar models.

Many sequential decision making problems under uncertainty arising in engineering, science and economics are often modelled as Markov Decision Processes (MDPs). In the setting of MDPs, the goal is to and a state dependent optimal sequence of actions that minimizes a certain long-term performance criterion. The standard dynamic programming approach to solve an MDP for the optimal decisions requires a complete model of the MDP and is computationally feasible only for small state-action MDPs. Reinforcement learning (RL) methods, on the other hand, are model-free simulation based approaches for solving MDPs. In many real world applications, one is often faced with MDPs that have large state-action spaces whose model is unknown, however, whose outcomes can be simulated. In order to solve such (large) MDPs, one either resorts to the technique of function approximation in conjunction with RL methods or develops application specific RL methods. A solution based on RL methods with function approximation comes with the associated problem of choosing the right features for approximation and a solution based on application specific RL methods primarily relies on utilizing the problem structure. In this thesis, we investigate the problem of choosing the right features for RL methods based on function approximation as well as develop novel RL algorithms that adaptively obtain best features for approximation. Subsequently, we also develop problem specie RL methods for applications arising in the areas of wireless sensor networks and road traffic control. In the first part of the thesis, we consider the problem of finding the best features for value function approximation in reinforcement learning for the long-run discounted cost objective. We quantify the error in the approximation for any given feature and the approximation parameter by the mean square Bellman error (MSBE) objective and develop an online algorithm to optimize MSBE. Subsequently, we propose the first online actor-critic scheme with adaptive bases to find a locally optimal (control) policy for an MDP under the weighted discounted cost objective. The actor performs gradient search in the space of policy parameters using simultaneous perturbation stochastic approximation (SPSA) gradient estimates. This gradient computation however requires estimates of the value function of the policy. The value function is approximated using a linear architecture and its estimate is obtained from the critic. The error in approximation of the value function, however, results in sub-optimal policies. Thus, we obtain the best features by performing a gradient descent on the Grassmannian of features to minimize a MSBE objective. We provide a proof of convergence of our control algorithm to a locally optimal policy and show numerical results illustrating the performance of our algorithm. In our next work, we develop an online actor-critic control algorithm with adaptive feature tuning for MDPs under the long-run average cost objective. In this setting, a gradient search in the policy parameters is performed using policy gradient estimates to improve the performance of the actor. The computation of the aforementioned gradient however requires estimates of the differential value function of the policy. In order to obtain good estimates of the differential value function, the critic adaptively tunes the features to obtain the best representation of the value function using gradient search in the Grassmannian of features. We prove that our actor-critic algorithm converges to a locally optimal policy. Experiments on two different MDP settings show performance improvements resulting from our feature adaptation scheme. In the second part of the thesis, we develop problem specific RL solution methods for the two aforementioned applications. In both the applications, the size of the state-action space in the formulated MDPs is large. However, by utilizing the problem structure we develop scalable RL algorithms. In the wireless sensor networks application, we develop RL algorithms to find optimal energy management policies (EMPs) for energy harvesting (EH) sensor nodes. First, we consider the case of a single EH sensor node and formulate the problem of finding an optimal EMP in the discounted cost MDP setting. We then propose two RL algorithms to maximize network performance. Through simulations, our algorithms are seen to outperform the algorithms in the literature. Our RL algorithms for the single EH sensor node do not scale when there are multiple sensor nodes. In our second work, we consider the problem of finding optimal energy sharing policies that maximize the network performance of a system comprising of multiple sensor nodes and a single energy harvesting (EH) source. We develop efficient energy sharing algorithms, namely Q-learning algorithm with exploration mechanisms based on the -greedy method as well as upper confidence bound (UCB). We extend these algorithms by incorporating state and action space aggregation to tackle state-action space explosion in the MDP. We also develop a cross entropy based method that incorporates policy parameterization in order to find near optimal energy sharing policies. Through numerical experiments, we show that our algorithms yield energy sharing policies that outperform the heuristic greedy method. In the context of road traffic control, optimal control of traffic lights at junctions or traffic signal control (TSC) is essential for reducing the average delay experienced by the road users. This problem is hard to solve when simultaneously considering all the junctions in the road network. So, we propose a decentralized multi-agent reinforcement learning (MARL) algorithm for solving this problem by considering each junction in the road network as a separate agent (controller) to obtain dynamic TSC policies. We propose two approaches to minimize the average delay. In the first approach, each agent decides the signal duration of its phases in a round-robin (RR) manner using the multi-agent Q-learning algorithm. We show through simulations over VISSIM (microscopic traffic simulator) that our round-robin MARL algorithms perform significantly better than both the standard fixed signal timing (FST) algorithm and the saturation balancing (SAT) algorithm over two real road networks. In the second approach, instead of optimizing green light duration, each agent optimizes the order of the phase sequence. We then employ our MARL algorithms by suitably changing the state-action space and cost structure of the MDP. We show through simulations over VISSIM that our non-round robin MARL algorithms perform significantly better than the FST, SAT and the round-robin MARL algorithms based on the first approach. However, on the other hand, our round-robin MARL algorithms are more practically viable as they conform with the psychology of road users.

In Chapter 2, we propose several two-timescale simulation-based actor-critic algorithms for solution of infinite horizon Markov Decision Processes (MDPs) with finite state-space under the average cost criterion. On the slower timescale, all the algorithms perform a gradient search over corresponding policy spaces using two different Simultaneous Perturbation Stochastic Approximation (SPSA) gradient estimates. On the faster timescale, the differential cost function corresponding to a given stationary policy is updated and averaged for enhanced performance. A proof of convergence to a locally optimal policy is presented. Next, a memory efficient implementation using a feature-vector representation of the state-space and TD (0) learning along the faster timescale is discussed. A three-timescale simulation based algorithm for solution of infinite horizon discounted-cost MDPs via the Value Iteration approach is also proposed. An approximation of the Dynamic Programming operator T is applied to the value function iterates. A sketch of convergence explaining the dynamics of the algorithm using associated ODEs is presented. Numerical experiments on rate based flow control on a bottleneck node using a continuous-time queueing model are presented using the proposed algorithms. Next, in Chapter 3, we develop three simulation-based algorithms for finite-horizon MDPs (FHMDPs). The first algorithm is developed for finite state and compact action spaces while the other two are for finite state and finite action spaces. Convergence analysis is briefly sketched. We then concentrate on methods to mitigate the curse of dimensionality that affects FH-MDPs severely, as there is one probability transition matrix per stage. Two parametrized actor-critic algorithms for FHMDPs with compact action sets are proposed, the ‘critic’ in both algorithms learning the policy gradient. We show w.p1convergence to a set with the necessary condition for constrained optima. Further, a third algorithm for stochastic control of stopping time processes is presented. Numerical experiments with the proposed finite-horizon algorithms are shown for a problem of flow control in communication networks. Towards stochastic optimization, in Chapter 4, we propose five algorithms which are variants of SPSA. The original one measurement SPSA uses an estimate of the gradient of objective function L containing an additional bias term not seen in two-measurement SPSA. We propose a one-measurement algorithm that eliminates this bias, and has asymptotic convergence properties making for easier comparison with the two-measurement SPSA. The algorithm, under certain conditions, outperforms both forms of SPSA with the only overhead being the storage of a single measurement. We also propose a similar algorithm that uses perturbations obtained from normalized Hadamard matrices. The convergence w.p.1 of both algorithms is established. We extend measurement reuse to design three second-order SPSA algorithms, sketch the convergence analysis and present simulation results on an illustrative minimization problem. We then propose several stochastic approximation implementations for related algorithms in flow-control of communication networks, beginning with a discrete-time implementation of Kelly’s primal flow-control algorithm. Convergence with probability1 is shown, even in the presence of communication delays and stochastic effects seen in link congestion indications. Two relevant enhancements are then pursued :a) an implementation of the primal algorithm using second-order information, and b) an implementation where edge-routers rectify misbehaving flows. Also, discrete-time implementations of Kelly’s dual algorithm and primal-dual algorithm are proposed. Simulation results a) verifying the proposed algorithms and, b) comparing stability properties with an algorithm in the literature are presented.