A State Aggregation Approach for Solving Knapsack Problem with Deep Reinforcement Learning

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademic

23 Downloads (Pure)

Samenvatting

This paper proposes a Deep Reinforcement Learning (DRL) approach for solving knapsack problem. The proposed method consists of a state aggregation step based on tabular reinforcement learning to extract features and construct states. The state aggregation policy is applied to each problem instance of the knapsack problem, which is used with Advantage Actor Critic (A2C) algorithm to train a policy through which the items are sequentially selected at each time step. The method is a constructive solution approach and the process of selecting items is repeated until the final solution is obtained. The experiments show that our approach provides close to optimal solutions for all tested instances, outperforms the greedy algorithm, and is able to handle larger instances and more flexible than an existing DRL approach. In addition, the results demonstrate that the proposed model with the state aggregation strategy not only gives better solutions but also learns in less timesteps, than the one without state aggregation.
Originele taal-2Engels
Artikelnummer2004.12117
Aantal pagina's17
TijdschriftarXiv
StatusGepubliceerd - 25 apr 2020

Vingerafdruk Duik in de onderzoeksthema's van 'A State Aggregation Approach for Solving Knapsack Problem with Deep Reinforcement Learning'. Samen vormen ze een unieke vingerafdruk.

Citeer dit