|
|
|
|
|
 |
Search published articles |
 |
|
Showing 2 results for Markov Decision Process
Lalwani, Kumar, Spedicato, Gupta,
Volume 3, Issue 1 (4-2012)
Abstract
We present an application of ABS algorithms for multiple sequence alignment (MSA). The Markov decision process (MDP) based model leads to a linear programming problem (LPP), whose solution is linked to a suggested alignment. The important features of our work include the facility of alignment of multiple sequences simultaneously and no limit for the length of the sequences. Our goal here is to avoid the excessive computing time, needed by dynamic programming based algorithms for alignment of a large number of sequences. In an attempt to demonstrate the integration of the ABS approach with complex mathematical frameworks, we apply the ABS implicit LX algorithm to elucidate the LPP, constructed with the assistance of MDP. The MDP applied for MSA is a pragmatic approach and entails a scope for future work. Programming is done in the MATLAB environment
Sara Motamed,
Volume 16, Issue 2 (8-2025)
Abstract
This paper presents a constrained multi-objective deep reinforcement learning framework for urban traffic signal control. The problem is modeled as a constrained Markov decision process in which an agent simultaneously optimizes efficiency objectives while respecting explicit safety and fairness constraints. A dueling double deep Q-network (D3QN) is combined with a Lagrangian cost estimator to approximate both the reward value function and cumulative constraint costs. The state representation includes queue lengths, phase indicators and elapsed green times, and the action space consists of a small set of interpretable decisions such as extending the current green or switching to the next phase. The proposed controller is trained and evaluated in a SUMO-based microscopic simulation of a four-leg urban intersection under various traffic demand patterns. Its performance is compared with fixed-time, vehicle-actuated and unconstrained DQN controllers. Simulation results show that the proposed method can substantially reduce average delay and maximum queue length while keeping queue spillback and delay imbalance within predefined limits. These findings indicate that constrained multi-objective deep reinforcement learning offers a promising and practically deployable framework for safe and fair traffic signal control in congested urban networks, and can be extended to more complex corridors and network-wide settings in future work.
|
|
|
|
|
|
|
|
|
