IPPO Learns the Game, Not the Team: A Study on Generalization in Heterogeneous Agent Teams

• URL: http://arxiv.org/abs/2512.08877v2
• Date: Mon, 09 Mar 2026 02:44:05 GMT
• Title: IPPO Learns the Game, Not the Team: A Study on Generalization in Heterogeneous Agent Teams
• Abstract summary: Multi-Agent Reinforcement Learning (MARL) is commonly deployed in settings where agents are trained via self-play with homogeneous teammates.<n>This paper investigates what extent do self-play PPO agents learn general coordination strategies grounded in the underlying game, compared to overfitting to their training partners' behaviors.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-Agent Reinforcement Learning (MARL) is commonly deployed in settings where agents are trained via self-play with homogeneous teammates, often using parameter sharing and a single policy architecture. This opens the question: to what extent do self-play PPO agents learn general coordination strategies grounded in the underlying game, compared to overfitting to their training partners' behaviors? This paper investigates the question using the Heterogeneous Multi-Agent Challenge (HeMAC) environment, which features distinct Observer and Drone agents with complementary capabilities. We introduce Rotating Policy Training (RPT), an approach that rotates heterogeneous teammate policies of different learning algorithms during training, to expose the agent to a broader range of partner strategies. When playing alongside a withheld teammate policy (DDQN), we find that RPT achieves similar performance to a standard self-play baseline, IPPO, where all agents were trained sharing a single PPO policy. This result indicates that in this heterogeneous multi-agent setting, the IPPO baseline generalizes to novel teammate algorithms despite not experiencing teammate diversity during training. This shows that a simple IPPO baseline may possess the level of generalization to novel teammates that a diverse training regimen was designed to achieve.

Related papers

• On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations [15.549340968605234]
  Federated reinforcement learning (FedRL) enables multiple agents to collaboratively learn a policy without sharing their local trajectories collected during agent-environment interactions.<n>We introduce a emphpersonalized FedRL framework (PFedRL) by taking advantage of possibly shared common structure among agents in heterogeneous environments.
  arXiv  Detail & Related papers  (2024-11-22T15:42:43Z)
• N-Agent Ad Hoc Teamwork [36.10108537776956]
  Current approaches to learning cooperative multi-agent behaviors assume relatively restrictive settings. This paper formalizes the problem, and proposes the Policy Optimization with Agent Modelling (POAM) algorithm. POAM is a policy gradient, multi-agent reinforcement learning approach to the NAHT problem, that enables adaptation to diverse teammate behaviors.
  arXiv  Detail & Related papers  (2024-04-16T17:13:08Z)
• Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behaviors and Adversarial Style Sampling for Assistive Tasks [51.00472376469131]
  We propose a framework that learns a robust caregiver's policy by training it for diverse care-receiver responses. We demonstrate that policies trained with a popular deep RL method are vulnerable to changes in policies of other agents.
  arXiv  Detail & Related papers  (2024-03-01T08:15:18Z)
• ProAgent: Building Proactive Cooperative Agents with Large Language Models [89.53040828210945]
  ProAgent is a novel framework that harnesses large language models to create proactive agents. ProAgent can analyze the present state, and infer the intentions of teammates from observations. ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various coordination scenarios.
  arXiv  Detail & Related papers  (2023-08-22T10:36:56Z)
• Learning From Good Trajectories in Offline Multi-Agent Reinforcement Learning [98.07495732562654]
  offline multi-agent reinforcement learning (MARL) aims to learn effective multi-agent policies from pre-collected datasets. One agent learned by offline MARL often inherits this random policy, jeopardizing the performance of the entire team. We propose a novel framework called Shared Individual Trajectories (SIT) to address this problem.
  arXiv  Detail & Related papers  (2022-11-28T18:11:26Z)
• Learning Heterogeneous Agent Cooperation via Multiagent League Training [6.801749815385998]
  This work proposes a general-purpose reinforcement learning algorithm named Heterogeneous League Training (HLT) to address heterogeneous multiagent problems. HLT keeps track of a pool of policies that agents have explored during training, gathering a league of heterogeneous policies to facilitate future policy optimization. A hyper-network is introduced to increase the diversity of agent behaviors when collaborating with teammates having different levels of cooperation skills.
  arXiv  Detail & Related papers  (2022-11-13T13:57:15Z)
• RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning [90.43925357575543]
  We propose ranked policy memory ( RPM) to collect diverse multi-agent trajectories for training MARL policies with good generalizability. RPM enables MARL agents to interact with unseen agents in multi-agent generalization evaluation scenarios and complete given tasks, and it significantly boosts the performance up to 402% on average.
  arXiv  Detail & Related papers  (2022-10-18T07:32:43Z)
• Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge? [100.48692829396778]
  Independent PPO (IPPO) is a form of independent learning in which each agent simply estimates its local value function. IPPO's strong performance may be due to its robustness to some forms of environment non-stationarity.
  arXiv  Detail & Related papers  (2020-11-18T20:29:59Z)
• Natural Emergence of Heterogeneous Strategies in Artificially Intelligent Competitive Teams [0.0]
  We develop a competitive multi agent environment called FortAttack in which two teams compete against each other. We observe a natural emergence of heterogeneous behavior amongst homogeneous agents when such behavior can lead to the team's success. We propose ensemble training, in which we utilize the evolved opponent strategies to train a single policy for friendly agents.
  arXiv  Detail & Related papers  (2020-07-06T22:35:56Z)
• Model-based Reinforcement Learning for Decentralized Multiagent Rendezvous [66.6895109554163]
  Underlying the human ability to align goals with other agents is their ability to predict the intentions of others and actively update their own plans. We propose hierarchical predictive planning (HPP), a model-based reinforcement learning method for decentralized multiagent rendezvous.
  arXiv  Detail & Related papers  (2020-03-15T19:49:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.