Abstract
This paper explores the combination of model-based methods and multi-agent reinforcement learning (MARL) for more efficient coordination among multiple agents. A decentralized model-based MARL method, Policy Optimization with Dynamic Dependence Modeling (POD2M), is proposed to dynamically determine the importance of other agents’ information during the model building process. In POD2M, the agents adapt their mutual dependence during building their own dynamic models in order to make a trade-off between an individual-learning process and a coordinated-learning process. Once the dynamic models have been built, the policies are then trained based on one-step model predictive rollouts. Empirical experiments on both cooperative and competitive scenarios indicate that our method can achieve higher sample efficiency against the compared model-free MARL algorithms, and outperforms the centralized method in large domains.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)
Toyama, D., et al.: Androidenv: a reinforcement learning platform for android. arXiv preprint arXiv:2105.13231 (2021)
Luo, Y., Xu, H., Li, Y., Tian, Y., Darrell, T., Ma, T.: Algorithmic framework for model-based deep reinforcement learning with theoretical guarantees. arXiv preprint arXiv:1807.03858 (2018)
Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In International Conference on Machine Learning, pp. 387–395. PMLR (2014)
Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889–1897. PMLR (2015)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861–1870. PMLR (2018)
Moerland, T.M., Broekens, J., Jonker, C.M.: Model-based reinforcement learning: a survey. arXiv preprint arXiv:2006.16712 (2020)
Hafner, D., et al.: Learning latent dynamics for planning from pixels. In: International Conference on Machine Learning, pp. 2555–2565. PMLR (2019)
Schrittwieser, J., et al.: Mastering atari, go, chess and shogi by planning with a learned model. Nature 588(7839), 604–609 (2020)
Todorov, E., Erez, T., Tassa, Y.: Mujoco: a physics engine for model-based control. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 5026–5033. IEEE (2012)
Chao, Yu., Dong, Y., Li, Y., Chen, Y.: Distributed multi-agent deep reinforcement learning for cooperative multi-robot pursuit. J. Eng. 2020(13), 499–504 (2020)
Vinyals, O., et al.: Starcraft II: a new challenge for reinforcement learning. arXiv preprint arXiv:1708.04782 (2017)
Wu, Z., Yu, C., Ye, D., Zhang, J., Piao, H., Zhuo, H.H.: Coordinated proximal policy optimization. arXiv preprint arXiv:2111.04051 (2021)
Wang, R.E., et al.: Model-based reinforcement learning for decentralized multiagent rendezvous. In Conference on Robot Learning (CoRL), pp. 711–725 (2020)
Chao, Yu., et al.: Distributed multiagent coordinated learning for autonomous driving in highways based on dynamic coordination graphs. IEEE Trans. Intell. Transp. Syst. 21(2), 735–748 (2019)
Willemsen, D., Coppola, M., Che de Croon, G.: Mambpo: sample-efficient multi-robot reinforcement learning using learned world models. arXiv preprint arXiv:2103.03662 (2021)
Chao, Yu., Zhang, M., Ren, F., Tan, G.: Multiagent learning of coordination in loosely coupled multiagent systems. IEEE Trans. Cybernet. 45(12), 2853–2867 (2015)
Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, pp. 6382–6393 (2017)
Nagabandi, A., Kahn, G., Fearing, R.S., Levine, S.: Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 7559–7566. IEEE (2018)
Chua, K., Calandra, R., McAllister, R., Levine, S.: Deep reinforcement learning in a handful of trials using probabilistic dynamics models. In: Advances in Neural Information Processing Systems, pp. 4759–4770 (2018)
Sutton, R.S.: Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In: Machine Learning Proceedings 1990, pp. 216–224. Elsevier (1990)
Wang, T., Ba, J.: Exploring model-based planning with policy networks. arXiv preprint arXiv:1906.08649 (2019)
Feinberg, V., Wan, A., Stoica, I., Jordan, M.I., Gonzalez, J.E., Levine, S.: Model-based value estimation for efficient model-free reinforcement learning. arXiv preprint arXiv:1803.00101 (2018)
Clavera, I., Fu, V., Abbeel, P.: Model-augmented actor-critic: Backpropagating through paths. In: International Conference on Learning Representations (2020)
Janner, M., Fu, J., Zhang, M., Levine, S.: When to trust your model: model-based policy optimization. In: Advances in Neural Information Processing Systems, pp. 12498–12509 (2019)
Rajeswaran, A., Mordatch, I., Kumar, V.: A game theoretic framework for model based reinforcement learning. In: International Conference on Machine Learning, pp. 7953–7963. PMLR (2020)
Iqbal, S., Sha, F.: Actor-attention-critic for multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 2961–2970. PMLR (2019)
Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)
Du, Y., Han, L., Fang, M., Liu, J., Dai, T., Tao, D.: Liir: learning individual intrinsic reward in multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 4403–4414 (2019)
Wang, T., Dong, H., Lesser, V., Zhang, C.: Roma: multi-agent reinforcement learning with emergent roles. In: International Conference on Machine Learning, pp. 9876–9886 (2020)
Park, Y.J., Cho, Y.S., Kim, S.B.: Multi-agent reinforcement learning with approximate model learning for competitive games. PLoS ONE 14(9), e0222215 (2019)
Zhang, W., Wang, X., Shen, J., Zhou, M.: Model-based multi-agent policy optimization with adaptive opponent-wise rollouts. arXiv preprint arXiv:2105.03363 (2021)
Konda, V.R., Tsitsiklis, J.N.: Actor-critic algorithms. In: Advances in Neural Information Processing Systems, pp. 1008–1014 (2000)
Kurutach, T., Clavera, I., Duan, Y., Tamar, A., Abbeel, P.: Model-ensemble trust-region policy optimization. In: International Conference on Learning Representations (2018)
D’Oro, P., Jaśkowski, W.: How to learn a useful critic? Model-based action-gradient-estimator policy optimization. In: Advances in Neural Information Processing Systems, pp. 313–324 (2020)
Sukhbaatar, S., Fergus, R., et al.: Learning multiagent communication with backpropagation. In: Advances in Neural Information Processing Systems, pp. 2244–2252 (2016)
Wang, T., Wang, J., Wu, Y., Zhang, C.: Influence-based multi-agent exploration. In: International Conference on Learning Representations (2019)
He, H., Boyd-Graber, J., Kwok, K., Daumé III, H.: Opponent modeling in deep reinforcement learning. In: International Conference on Machine Learning, pp. 1804–1813. PMLR (2016)
Vaswani, A., et al.:. Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, pp. 2974–2982 (2018)
Samvelyan, M., et al.: The starcraft multi-agent challenge. In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 2186–2188 (2019)
Acknowledgement
This work is supported by the National Natural Science Foundation of China under Grant 62076259.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Hu, B., Yu, C., Wu, Z. (2022). Model-Based Multi-agent Policy Optimization with Dynamic Dependence Modeling. In: Shen, H., et al. Parallel and Distributed Computing, Applications and Technologies. PDCAT 2021. Lecture Notes in Computer Science(), vol 13148. Springer, Cham. https://doi.org/10.1007/978-3-030-96772-7_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-96772-7_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96771-0
Online ISBN: 978-3-030-96772-7
eBook Packages: Computer ScienceComputer Science (R0)