MTMA-DDPG: A Deep Deterministic Policy Gradient Reinforcement Learning for Multi-task Multi-agent Environments - Artificial Intelligence Applications and Innovations Access content directly
Conference Papers Year : 2022

MTMA-DDPG: A Deep Deterministic Policy Gradient Reinforcement Learning for Multi-task Multi-agent Environments

Karim Hamadeh
  • Function : Author
  • PersonId : 1318728
Julia El Zini
  • Function : Author
  • PersonId : 1318729
Joudi Hajar
  • Function : Author
  • PersonId : 1318730
Mariette Awad
  • Function : Author
  • PersonId : 1318731

Abstract

Beyond Multi-Task or Multi-Agent learning, we develop in this work a multi-agent reinforcement learning algorithm to handle a multi-task environments. Our proposed algorithm, Multi-Task Multi-Agent Deep Deterministic Policy gradient, (MTMA-DDPG) (Code available at https://gitlab.com/awadailab/mtmaddpg ), extends its single task counterpart by running multiple tasks on distributed nodes and communicating parameters via pre-determined coefficients across the nodes. Parameter sharing is modulated through temporal decay of the communication coefficients. Training across nodes is parallelized without any centralized controller for different tasks, which opens horizons for flexible leveraging and parallel processing to improve MA learning.Empirically, we design different MA particle environments, where tasks are similar or heterogeneous. We study the performance of MTMA-DDPG in terms of reward, convergence, variance, and communication overhead. We demonstrate the improvement of our algorithm over its single-task counterpart, as well as the importance of a versatile technique to take advantage of parallel computing resources.
Embargoed file
Embargoed file
0 7 18
Year Month Jours
Avant la publication
Wednesday, January 1, 2025
Embargoed file
Wednesday, January 1, 2025
Please log in to request access to the document

Dates and versions

hal-04317184 , version 1 (01-12-2023)

Licence

Attribution

Identifiers

Cite

Karim Hamadeh, Julia El Zini, Joudi Hajar, Mariette Awad. MTMA-DDPG: A Deep Deterministic Policy Gradient Reinforcement Learning for Multi-task Multi-agent Environments. 18th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2022, Hersonissos, Greece. pp.270-281, ⟨10.1007/978-3-031-08333-4_22⟩. ⟨hal-04317184⟩
23 View
1 Download

Altmetric

Share

Gmail Facebook X LinkedIn More