English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

There is a growing interest in integrating machine learning techniques andoptimization to solve challenging optimization problems. In this work, wepropose a deep reinforcement learning methodology for the job shop schedulingproblem (JSSP). The aim is to build up a greedy-like heuristic able to learn onsome distribution of JSSP instances, different in the number of jobs andmachines. The need for fast scheduling methods is well known, and it arises inmany areas, from transportation to healthcare. We model the JSSP as a MarkovDecision Process and then we exploit the efficacy of reinforcement learning tosolve the problem. We adopt an actor-critic scheme, where the action taken bythe agent is influenced by policy considerations on the state-value function.The procedures are adapted to take into account the challenging nature of JSSP,where the state and the action space change not only for every instance butalso after each decision. To tackle the variability in the number of jobs andoperations in the input, we modeled the agent using two incident LSTM models, aspecial type of deep neural network. Experiments show the algorithm reachesgood solutions in a short time, proving that is possible to generate new greedyheuristics just from learning-based methodologies. Benchmarks have beengenerated in comparison with the commercial solver CPLEX. As expected, themodel can generalize, to some extent, to larger problems or instancesoriginated by a different distribution from the one used in training.

An actor-critic algorithm with policy gradients to solve the job shop scheduling problem using deep double recurrent agents