Experts in a Markov Decision Process
نویسندگان
چکیده
We consider an MDP setting in which the reward function is allowed to change during each time step of play (possibly in an adversarial manner), yet the dynamics remain fixed. Similar to the experts setting, we address the question of how well can an agent do when compared to the reward achieved under the best stationary policy over time. We provide efficient algorithms, which have regret bounds with no dependence on the size of state space. Instead, these bounds depend only on a certain horizon time of the process and logarithmically on the number of actions. We also show that in the case that the dynamics change over time, the problem becomes computationally hard.
منابع مشابه
Optimizing Red Blood Cells Consumption Using Markov Decision Process
In healthcare systems, one of the important actions is related to perishable products such as red blood cells (RBCs) units that its consumption management in different periods can contribute greatly to the optimality of the system. In this paper, main goal is to enhance the ability of medical community to organize the RBCs units’ consumption in way to deliver the unit order timely with a focus ...
متن کاملA new machine replacement policy based on number of defective items and Markov chains
A novel optimal single machine replacement policy using a single as well as a two-stage decision making process is proposed based on the quality of items produced. In a stage of this policy, if the number of defective items in a sample of produced items is more than an upper threshold, the machine is replaced. However, the machine is not replaced if the number of defective items is less than ...
متن کاملAccelerated decomposition techniques for large discounted Markov decision processes
Many hierarchical techniques to solve large Markov decision processes (MDPs) are based on the partition of the state space into strongly connected components (SCCs) that can be classified into some levels. In each level, smaller problems named restricted MDPs are solved, and then these partial solutions are combined to obtain the global solution. In this paper, we first propose a novel algorith...
متن کاملAn Experts Algorithm for Transfer Learning
A long-lived agent continually faces new tasks in its environment. Such an agent may be able to use knowledge learned in solving earlier tasks to produce candidate policies for its current task. There may, however, be multiple reasonable policies suggested by prior experience, and the agent must choose between them potentially without any a priori knowledge about their applicability to its curr...
متن کاملA POMDP Framework to Find Optimal Inspection and Maintenance Policies via Availability and Profit Maximization for Manufacturing Systems
Maintenance can be the factor of either increasing or decreasing system's availability, so it is valuable work to evaluate a maintenance policy from cost and availability point of view, simultaneously and according to decision maker's priorities. This study proposes a Partially Observable Markov Decision Process (POMDP) framework for a partially observable and stochastically deteriorating syste...
متن کامل