Combining Planning and Reinforcement Learning for Solving Relational Multiagent Domains

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Prabhakar, Nikhilesh, Singh, Ranveer, Kokel, Harsha, Natarajan, Sriraam, Tadepalli, Prasad
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913708304760832
author Prabhakar, Nikhilesh
Singh, Ranveer
Kokel, Harsha
Natarajan, Sriraam
Tadepalli, Prasad
author_facet Prabhakar, Nikhilesh
Singh, Ranveer
Kokel, Harsha
Natarajan, Sriraam
Tadepalli, Prasad
contents Multiagent Reinforcement Learning (MARL) poses significant challenges due to the exponential growth of state and action spaces and the non-stationary nature of multiagent environments. This results in notable sample inefficiency and hinders generalization across diverse tasks. The complexity is further pronounced in relational settings, where domain knowledge is crucial but often underutilized by existing MARL algorithms. To overcome these hurdles, we propose integrating relational planners as centralized controllers with efficient state abstractions and reinforcement learning. This approach proves to be sample-efficient and facilitates effective task transfer and generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2502_19297
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Combining Planning and Reinforcement Learning for Solving Relational Multiagent Domains
Prabhakar, Nikhilesh
Singh, Ranveer
Kokel, Harsha
Natarajan, Sriraam
Tadepalli, Prasad
Multiagent Systems
Artificial Intelligence
Machine Learning
Multiagent Reinforcement Learning (MARL) poses significant challenges due to the exponential growth of state and action spaces and the non-stationary nature of multiagent environments. This results in notable sample inefficiency and hinders generalization across diverse tasks. The complexity is further pronounced in relational settings, where domain knowledge is crucial but often underutilized by existing MARL algorithms. To overcome these hurdles, we propose integrating relational planners as centralized controllers with efficient state abstractions and reinforcement learning. This approach proves to be sample-efficient and facilitates effective task transfer and generalization.
title Combining Planning and Reinforcement Learning for Solving Relational Multiagent Domains
topic Multiagent Systems
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2502.19297