← Back to all news
arXiv Machine Learning By Fernando Martinez, Tao Li, Yingdong Lu, Juntao Chen

Independent Multi-Agent Reinforcement Learning with Counterfactual Semantic-Social World Models

Read the original on arXiv Machine Learning →

The paper introduces CASTLE, a framework for fully decentralized multi‑agent reinforcement learning that uses two offline‑trained world models to provide in‑context guidance to independent agents. A Local Dynamics World Model captures each agent’s trajectory dynamics, while a Semantic‑Social World Model predicts short‑horizon task and social outcomes for candidate actions based on counterfactual simulator rollouts. During online learning, these frozen models supply prediction logits to an independent PPO policy, enabling agents to compare potential actions prospectively rather than relying solely on scalar rewards. CASTLE outperforms existing baselines on several multi‑particle benchmark tasks, achieving the highest mean final scores across 30 seeds.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Oct 9

MA-JEPA: Joint-Embedding World Models for Multi-Agent Reinforcement Learning

MA-JEPA is a stochastic world model designed for multi‑agent reinforcement learning that replaces observation reconstruction with joint‑embedding prediction. It uses a categorical latent state and a causal Transformer trained on posterior and action‑conditioned dynamics to generate imagined trajectories for actor‑critic learning. The model achieves strong performance on the SMAC benchmark, matching or surpassing the best reported mean win rates on half of the evaluated maps.

By Brandon Gary Kaplowitz, Osaze James Obahor, Christian Schroeder de Witt
llmsragagentsreinforcement-learning
More like this →
arXiv Machine Learning
Sep 4

LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat Games

The paper explores a runtime strategy-selection framework where a large language model (LLM) guides a pre‑trained reinforcement learning (RL) policy for non‑player characters (NPCs) in a Unity combat game without altering the underlying policy. Five NPC agents sharing a PPO policy were compared in a baseline setup and an LLM‑augmented setup, where a locally hosted Mistral 7B model assigns one of four tactical tags every five seconds based on live game state. Across 600 episodes against three scripted opponents, the LLM‑augmented agents more than doubled their win rate against a Balanced opponent, improved performance against an Evasive opponent, but struggled against an Aggressive opponent due to over‑reliance on encirclement; analysis of 2,430 strategy selections revealed limited zero‑shot differentiation with the model favoring Surround in 83.8% of cases.

By Hrithika Deepu Nair, Kayvan Karim
llmsagentsreinforcement-learning
More like this →