The DOI matches its OpenAlex record; 1 of the 1 references it cites were found in a registry or an index.
The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games
Open accessAbstract
Proximal Policy Optimization (PPO) is a ubiquitous on-policy reinforcement learning algorithm but is significantly less utilized than off-policy learning algorithms in multi-agent settings. This is often due to the belief that PPO is significantly less sample efficient than off-policy methods in multi-agent systems. In this work, we carefully study the performance of PPO in cooperative multi-agent settings. We show that PPO-based multi-agent algorithms achieve surprisingly strong performance in four popular multi-agent testbeds: the particle-world environments, the StarCraft multi-agent challenge, Google Research Football, and the Hanabi challenge, with minimal hyperparameter tuning and without any domain-specific algorithmic modifications or architectures. Importantly, compared to competitive off-policy methods, PPO often achieves competitive or superior results in both final returns and sample efficiency. Finally, through ablation studies, we analyze implementation and hyperparameter factors that are critical to PPO's empirical performance, and give concrete practical suggestions regarding these factors. Our results show that when using these practices, simple PPO-based methods can be a strong baseline in cooperative multi-agent reinforcement learning. Source code is released at \url{https://github.com/marlbenchmark/on-policy}.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Soft actor-critic Off-policy maximum entropy deep reinforcement learning with a stochastic actor
Haarnoja, T., Zhou, A., Abbeel, P., & Levine, S. (2018) · arXiv · doi:10.48550/arxiv.1801.01290 · Cited by 5,594 · cited 2×
“In single-agent continuous control tasks [8], advances in off-policy methods such as SAC [13] led to a consensus that despite their early success, policy gradient (PG) algorithms such as PPO are less sample efficient than off-policy methods.”
BackgroundMethod
Cited by
Transfer Learning in Deep Reinforcement Learning: A Survey
Zhu, Z., Lin, K., Jain, A. K., & Zhou, J. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3292075 · Cited by 861
“To encompass the episodic concept in infinite MDPs, episodic RL tasks usually assume the existence of a set of absorbing states S 0 , which indicates the termination of episodic tasks [18], [19], and any action taken upon an absorbing state will only transit to itself with zero rewards.”
BackgroundDeep Multi-Agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic
Chen, D., Hajidavalloo, M. R., Li, Z., Chen, K., Wang, Y., Jiang, L., & Wang, Y. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3285442 · Cited by 257
Self-citationProAgent: Building Proactive Cooperative Agents with Large Language Models
Zhang, C., Yang, K., Hu, S., Wang, Z., Li, G., Sun, Y., Zhang, C., Zhang, Z., Liu, A., Zhu, S.-C., et al. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i16.29710 · Cited by 88
“The goal of multi-agent coordination is to enable multiple autonomous agents to collaborate effectively towards a shared goal (Rashid et al. 2018; Hu and Foerster 2020; Hu et al. 2021a; Yu et al. 2022; Zhong et al. 2023).”
BackgroundTheory of Mind for Multi-Agent Collaboration via Large Language Models
Li, H., Chong, Y. Q., Stepputtis, S., Campbell, J., Hughes, D., Lewis, M., & Sycara, K. (2023) · arXiv · doi:10.48550/arxiv.2310.10701 · Cited by 82
Hua, M., Qi, X., Chen, D., Jiang, K., Liu, Z. E., Sun, H., Zhou, Q., & Xu, H. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3574280 · Cited by 88
“…expressed as: Hou et al. devise a decentralized cooperative lane-changing controller employing a multi-agent Proximal Policy Optimization (MAPPO) [115] approach, which empowers each vehicle to independently learn and assess its policy and action rewards based on local information, while still…”
Metadata
- Authors
- Yu, C., Velu, A., Vinitsky, E., Gao, J., Wang, Y., Bayen, A. M., & Wu, Y.
- Venue
- neural information processing systems
- Published
- 2022-01-01
- Pages
- 24611-24624
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133226216
- Cited by
- 1,027
- References
- 1
- FWCI
- 87.47
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.