Causal Knowledge Transfer for Multi-Agent Reinforcement Learning in Dynamic Environments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Korte, Kathrin, Adriano, Christian Medeiros, Ghahremani, Sona, Giese, Holger
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915398107004928
author Korte, Kathrin
Adriano, Christian Medeiros
Ghahremani, Sona
Giese, Holger
author_facet Korte, Kathrin
Adriano, Christian Medeiros
Ghahremani, Sona
Giese, Holger
contents [Context] Multi-agent reinforcement learning (MARL) has achieved notable success in environments where agents must learn coordinated behaviors. However, transferring knowledge across agents remains challenging in non-stationary environments with changing goals. [Problem] Traditional knowledge transfer methods in MARL struggle to generalize, and agents often require costly retraining to adapt. [Approach] This paper introduces a causal knowledge transfer framework that enables RL agents to learn and share compact causal representations of paths within a non-stationary environment. As the environment changes (new obstacles), agents' collisions require adaptive recovery strategies. We model each collision as a causal intervention instantiated as a sequence of recovery actions (a macro) whose effect corresponds to a causal knowledge of how to circumvent the obstacle while increasing the chances of achieving the agent's goal (maximizing cumulative reward). This recovery action macro is transferred online from a second agent and is applied in a zero-shot fashion, i.e., without retraining, just by querying a lookup model with local context information (collisions). [Results] Our findings reveal two key insights: (1) agents with heterogeneous goals were able to bridge about half of the gap between random exploration and a fully retrained policy when adapting to new environments, and (2) the impact of causal knowledge transfer depends on the interplay between environment complexity and agents' heterogeneous goals.
format Preprint
id arxiv_https___arxiv_org_abs_2507_13846
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Causal Knowledge Transfer for Multi-Agent Reinforcement Learning in Dynamic Environments
Korte, Kathrin
Adriano, Christian Medeiros
Ghahremani, Sona
Giese, Holger
Artificial Intelligence
[Context] Multi-agent reinforcement learning (MARL) has achieved notable success in environments where agents must learn coordinated behaviors. However, transferring knowledge across agents remains challenging in non-stationary environments with changing goals. [Problem] Traditional knowledge transfer methods in MARL struggle to generalize, and agents often require costly retraining to adapt. [Approach] This paper introduces a causal knowledge transfer framework that enables RL agents to learn and share compact causal representations of paths within a non-stationary environment. As the environment changes (new obstacles), agents' collisions require adaptive recovery strategies. We model each collision as a causal intervention instantiated as a sequence of recovery actions (a macro) whose effect corresponds to a causal knowledge of how to circumvent the obstacle while increasing the chances of achieving the agent's goal (maximizing cumulative reward). This recovery action macro is transferred online from a second agent and is applied in a zero-shot fashion, i.e., without retraining, just by querying a lookup model with local context information (collisions). [Results] Our findings reveal two key insights: (1) agents with heterogeneous goals were able to bridge about half of the gap between random exploration and a fully retrained policy when adapting to new environments, and (2) the impact of causal knowledge transfer depends on the interplay between environment complexity and agents' heterogeneous goals.
title Causal Knowledge Transfer for Multi-Agent Reinforcement Learning in Dynamic Environments
topic Artificial Intelligence
url https://arxiv.org/abs/2507.13846