9 articles
Approximate dynamic programming
Approximate dynamic programming (ADP) is a family of computational methods that approximate value functions in large-scale decision problems where exact dynamic programming is intractable, known in other fields as neuro-dynamic programming and reinforcement learning.
Feedback optimization
Feedback optimization is a control method that adjusts a system's decision variables in real time from noisy measurements, driving it to the solution of an optimization problem.
Forward algorithm
The forward algorithm is a dynamic programming algorithm that computes the likelihood of an observed sequence under a hidden Markov model, summing over all hidden state paths in O(N²T) time instead of exponentially.
Lyapunov optimization
Lyapunov optimization is an online control framework for stochastic networks that stabilizes queues while optimizing time-average objectives, making greedy per-slot decisions from current queue states alone.
Real-time optimization
Real-time optimization (RTO) is a model-based method that repeatedly re-solves a plant's steady-state economic optimization using current measurements, sending optimal setpoints to lower control layers.
Resource-constrained project scheduling
Resource-constrained project scheduling (RCPSP) is the NP-hard operations research problem of scheduling project activities under precedence relations and resource limits to minimize the makespan, first formulated in 1967.
Rolling horizon optimization
Rolling horizon optimization is a decision method that repeatedly solves an optimization model over a moving time window, implementing only immediate decisions before re-solving as new information arrives.
Time-varying optimization
Time-varying optimization is the task of minimizing a convex problem whose objective and feasible set change continuously in time, so algorithms track the moving optimum rather than converge.
Value iteration
Value iteration is a dynamic programming algorithm that computes the optimal value function and policy for a Markov decision process, first proposed by Richard Bellman in 1957.