Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach

• URL: http://arxiv.org/abs/2105.08268v1
• Date: Tue, 18 May 2021 04:35:41 GMT
• Title: Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach
• Authors: Yan Li, Lingxiao Wang, Jiachen Yang, Ethan Wang, Zhaoran Wang, Tuo Zhao, Hongyuan Zha
• Abstract summary: We propose the mean-field proximal policy optimization (MF-PPO) algorithm, at the core of which is a permutation-invariant actor-critic neural architecture. We prove that MF-PPO attains the globally optimal policy at a sublinear rate of convergence. In particular, we show that the inductive bias introduced by the permutation-invariant neural architecture enables MF-PPO to outperform existing competitors.
• Score: 128.62787284435007
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-agent reinforcement learning (MARL) becomes more challenging in the presence of more agents, as the capacity of the joint state and action spaces grows exponentially in the number of agents. To address such a challenge of scale, we identify a class of cooperative MARL problems with permutation invariance, and formulate it as a mean-field Markov decision processes (MDP). To exploit the permutation invariance therein, we propose the mean-field proximal policy optimization (MF-PPO) algorithm, at the core of which is a permutation-invariant actor-critic neural architecture. We prove that MF-PPO attains the globally optimal policy at a sublinear rate of convergence. Moreover, its sample complexity is independent of the number of agents. We validate the theoretical advantages of MF-PPO with numerical experiments in the multi-agent particle environment (MPE). In particular, we show that the inductive bias introduced by the permutation-invariant neural architecture enables MF-PPO to outperform existing competitors with a smaller number of model parameters, which is the key to its generalization performance.

Related papers

• On-the-fly Modulation for Balanced Multimodal Learning [53.616094855778954]
  Multimodal learning is expected to boost model performance by integrating information from different modalities. The widely-used joint training strategy leads to imbalanced and under-optimized uni-modal representations. We propose On-the-fly Prediction Modulation (OPM) and On-the-fly Gradient Modulation (OGM) strategies to modulate the optimization of each modality.
  arXiv  Detail & Related papers  (2024-10-15T13:15:50Z)
• Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL [57.745700271150454]
  We study the sample complexity of reinforcement learning in Mean-Field Games (MFGs) with model-based function approximation. We introduce the Partial Model-Based Eluder Dimension (P-MBED), a more effective notion to characterize the model class complexity.
  arXiv  Detail & Related papers  (2024-02-08T14:54:47Z)
• Pre-Evolved Model for Complex Multi-objective Optimization Problems [3.784829029016233]
  Multi-objective optimization problems (MOPs) necessitate the simultaneous optimization of multiple objectives. This paper proposes the concept of pre-evolving for MOEAs to generate high-quality populations for diverse complex MOPs.
  arXiv  Detail & Related papers  (2023-12-11T05:16:58Z)
• Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning [139.53668999720605]
  We present a multi-agent PPO algorithm in which the local policy of each agent is updated similarly to vanilla PPO. We prove that with standard regularity conditions on the Markov game and problem-dependent quantities, our algorithm converges to the globally optimal policy at a sublinear rate.
  arXiv  Detail & Related papers  (2023-05-08T16:20:03Z)
• Towards Global Optimality in Cooperative MARL with the Transformation And Distillation Framework [26.612749327414335]
  Decentralized execution is one core demand in cooperative multi-agent reinforcement learning (MARL) In this paper, we theoretically analyze two common classes of algorithms with decentralized policies -- multi-agent policy gradient methods and value-decomposition methods. We show that TAD-PPO can theoretically perform optimal policy learning in the finite multi-agent MDPs and shows significant outperformance on a large set of cooperative multi-agent tasks.
  arXiv  Detail & Related papers  (2022-07-12T06:59:13Z)
• Convergence Rates of Average-Reward Multi-agent Reinforcement Learning via Randomized Linear Programming [41.30044824711509]
  We focus on the case that the global reward is a sum of local rewards, the joint policy factorizes into agents' marginals, and full state observability. We develop multi-agent extensions, whereby agents solve their local saddle point problems and then perform local weighted averaging. We establish that the sample complexity to obtain near-globally optimal solutions matches tight dependencies on the cardinality of the state and action spaces.
  arXiv  Detail & Related papers  (2021-10-22T03:48:41Z)
• Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
  We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems. Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC. We provide a practical parametrization of the core optimization problem.
  arXiv  Detail & Related papers  (2021-07-08T18:01:02Z)
• Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts [52.844741540236285]
  This paper investigates the model-based methods in multi-agent reinforcement learning (MARL) We propose a novel decentralized model-based MARL method, named Adaptive Opponent-wise Rollout Policy (AORPO)
  arXiv  Detail & Related papers  (2021-05-07T16:20:22Z)

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.