skip to main content
Language:

On the Approximation of Cooperative Heterogeneous Multi-Agent Reinforcement Learning (MARL) using Mean Field Control (MFC)

Washim Uddin Mondal ; Agarwal, Mridul ; Aggarwal, Vaneet ; Ukkusuri, Satish V

arXiv.org, 2022-01 [Peer Reviewed Journal]

Ithaca: Cornell University Library, arXiv.org

Full text available

Citations Cited by
  • Title:
    On the Approximation of Cooperative Heterogeneous Multi-Agent Reinforcement Learning (MARL) using Mean Field Control (MFC)
  • Author: Washim Uddin Mondal ; Agarwal, Mridul ; Aggarwal, Vaneet ; Ukkusuri, Satish V
  • Subjects: Algorithms ; Approximation ; Computer Science - Artificial Intelligence ; Computer Science - Computer Science and Game Theory ; Computer Science - Learning ; Computer Science - Multiagent Systems ; Learning ; Mathematical analysis ; Multiagent systems
  • Is Part Of: arXiv.org, 2022-01
  • Description: Mean field control (MFC) is an effective way to mitigate the curse of dimensionality of cooperative multi-agent reinforcement learning (MARL) problems. This work considers a collection of \(N_{\mathrm{pop}}\) heterogeneous agents that can be segregated into \(K\) classes such that the \(k\)-th class contains \(N_k\) homogeneous agents. We aim to prove approximation guarantees of the MARL problem for this heterogeneous system by its corresponding MFC problem. We consider three scenarios where the reward and transition dynamics of all agents are respectively taken to be functions of \((1)\) joint state and action distributions across all classes, \((2)\) individual distributions of each class, and \((3)\) marginal distributions of the entire population. We show that, in these cases, the \(K\)-class MARL problem can be approximated by MFC with errors given as \(e_1=\mathcal{O}(\frac{\sqrt{|\mathcal{X}|}+\sqrt{|\mathcal{U}|}}{N_{\mathrm{pop}}}\sum_{k}\sqrt{N_k})\), \(e_2=\mathcal{O}(\left[\sqrt{|\mathcal{X}|}+\sqrt{|\mathcal{U}|}\right]\sum_{k}\frac{1}{\sqrt{N_k}})\) and \(e_3=\mathcal{O}\left(\left[\sqrt{|\mathcal{X}|}+\sqrt{|\mathcal{U}|}\right]\left[\frac{A}{N_{\mathrm{pop}}}\sum_{k\in[K]}\sqrt{N_k}+\frac{B}{\sqrt{N_{\mathrm{pop}}}\right]\right)\), respectively, where \(A, B\) are some constants and \(|\mathcal{X}|,|\mathcal{U}|\) are the sizes of state and action spaces of each agent. Finally, we design a Natural Policy Gradient (NPG) based algorithm that, in the three cases stated above, can converge to an optimal MARL policy within \(\mathcal{O}(e_j)\) error with a sample complexity of \(\mathcal{O}(e_j^{-3})\), \(j\in\{1,2,3\}\), respectively.
  • Publisher: Ithaca: Cornell University Library, arXiv.org
  • Language: English
Links
Back to results list
Result  1 NextGo to Next page

  • Implemented by: ABCD-USP USP   Social Network Logos: Freepik

Searching Remote Databases, Please Wait

  • Searching for
  • inscope:(USP_VIDEOS),scope:("PRIMO"),scope:(USP_FISICO),scope:(USP_EREVISTAS),scope:(USP),scope:(USP_EBOOKS),scope:(USP_PRODUCAO),primo_central_multiple_fe
  • Show me what you have so far