Improving monotonic optimization in heterogeneous multi-agent reinforcement learning with optimal marginal deterministic policy gradient

• URL: http://arxiv.org/abs/2507.09989v1
• Date: Mon, 14 Jul 2025 07:16:01 GMT
• Title: Improving monotonic optimization in heterogeneous multi-agent reinforcement learning with optimal marginal deterministic policy gradient
• Authors: Xiaoyang Yu, Youfang Lin, Shuo Wang, Sheng Han,
• Abstract summary: heterogeneous multi-agent reinforcement learning (MARL)<n>Objectively replace the sequentially computed $Q_psi*(s,a_1:i)$ with the Optimal Marginal Q function $phi_psi*(s,a_1:i)$ derived from Q-functions.<n>Generalized Q Critic (GQC) as the critic function, employing pessimistic uncertainty-constrained loss to optimize different Q-value estimations.
• Score: 18.64288030584699
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In heterogeneous multi-agent reinforcement learning (MARL), achieving monotonic improvement plays a pivotal role in enhancing performance. The HAPPO algorithm proposes a feasible solution by introducing a sequential update scheme, which requires independent learning with No Parameter-sharing (NoPS). However, heterogeneous MARL generally requires Partial Parameter-sharing (ParPS) based on agent grouping to achieve high cooperative performance. Our experiments prove that directly combining ParPS with the sequential update scheme leads to the policy updating baseline drift problem, thereby failing to achieve improvement. To solve the conflict between monotonic improvement and ParPS, we propose the Optimal Marginal Deterministic Policy Gradient (OMDPG) algorithm. First, we replace the sequentially computed $Q_{\psi}^s(s,a_{1:i})$ with the Optimal Marginal Q (OMQ) function $\phi_{\psi}^*(s,a_{1:i})$ derived from Q-functions. This maintains MAAD's monotonic improvement while eliminating the conflict through optimal joint action sequences instead of sequential policy ratio calculations. Second, we introduce the Generalized Q Critic (GQC) as the critic function, employing pessimistic uncertainty-constrained loss to optimize different Q-value estimations. This provides the required Q-values for OMQ computation and stable baselines for actor updates. Finally, we implement a Centralized Critic Grouped Actor (CCGA) architecture that simultaneously achieves ParPS in local policy networks and accurate global Q-function computation. Experimental results in SMAC and MAMuJoCo environments demonstrate that OMDPG outperforms various state-of-the-art MARL baselines.

Related papers

• Policy Optimization and Multi-agent Reinforcement Learning for Mean-variance Team Stochastic Games [1.430310470698995]
  We study a long-run mean-variance team game (MV-TSG)<n>MV-TSG has two main challenges. First, the variance metric is neither additive nor Markovian in a dynamic setting.<n>We propose a Mean-Variance Multi-Agent Policy Iteration (MV-MAPI) algorithm with a sequential update scheme.<n>We derive specific conditions for stationary points to be Nash equilibria, and further, strict local optima.
  arXiv  Detail & Related papers  (2025-03-28T16:21:05Z)
• Monte Carlo Policy Gradient Method for Binary Optimization [3.742634130733923]
  We develop a novel probabilistic model to sample the binary solution according to a parameterized policy distribution. For coherent exploration in discrete spaces, parallel Markov Chain Monte Carlo (MCMC) methods are employed. Convergence to stationary points in expectation of the policy gradient method is established.
  arXiv  Detail & Related papers  (2023-07-03T07:01:42Z)
• Symmetric (Optimistic) Natural Policy Gradient for Multi-agent Learning with Parameter Convergence [18.412945308419033]
  We investigate the global convergence of natural policy gradient approximation variants in multi-agent learning. We propose an algorithm for several standard multi-agent learning scenarios.
  arXiv  Detail & Related papers  (2022-10-23T18:27:04Z)
• Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees [56.848265937921354]
  Inverse reinforcement learning (IRL) aims to recover the reward function and the associated optimal policy. Many algorithms for IRL have an inherently nested structure. We develop a novel single-loop algorithm for IRL that does not compromise reward estimation accuracy.
  arXiv  Detail & Related papers  (2022-10-04T17:13:45Z)
• Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games [63.60117916422867]
  This paper focuses on the most basic setting of competitive multi-agent RL, namely two-player zero-sum Markov games. We propose a single-loop policy optimization method with symmetric updates from both agents, where the policy is updated via the entropy-regularized optimistic multiplicative weights update (OMWU) method. Our convergence results improve upon the best known complexities, and lead to a better understanding of policy optimization in competitive Markov games.
  arXiv  Detail & Related papers  (2022-10-03T16:05:43Z)
• First-order Policy Optimization for Robust Markov Decision Process [40.2022466644885]
  We consider the problem of solving robust Markov decision process (MDP) MDP involves a set of discounted, finite state, finite action space MDPs with uncertain transition kernels. For $(mathbfs,mathbfa)$-rectangular uncertainty sets, we establish several structural observations on the robust objective.
  arXiv  Detail & Related papers  (2022-09-21T18:10:28Z)
• Planning and Learning with Adaptive Lookahead [74.39132848733847]
  Policy Iteration (PI) algorithm alternates between greedy one-step policy improvement and policy evaluation. Recent literature shows that multi-step lookahead policy improvement leads to a better convergence rate at the expense of increased complexity per iteration. We propose for the first time to dynamically adapt the multi-step lookahead horizon as a function of the state and of the value estimate.
  arXiv  Detail & Related papers  (2022-01-28T20:26:55Z)
• Robust and Adaptive Temporal-Difference Learning Using An Ensemble of Gaussian Processes [70.80716221080118]
  The paper takes a generative perspective on policy evaluation via temporal-difference (TD) learning. The OS-GPTD approach is developed to estimate the value function for a given policy by observing a sequence of state-reward pairs. To alleviate the limited expressiveness associated with a single fixed kernel, a weighted ensemble (E) of GP priors is employed to yield an alternative scheme.
  arXiv  Detail & Related papers  (2021-12-01T23:15:09Z)
• Logistic Q-Learning [87.00813469969167]
  We propose a new reinforcement learning algorithm derived from a regularized linear-programming formulation of optimal control in MDPs. The main feature of our algorithm is a convex loss function for policy evaluation that serves as a theoretically sound alternative to the widely used squared Bellman error.
  arXiv  Detail & Related papers  (2020-10-21T17:14:31Z)
• Queueing Network Controls via Deep Reinforcement Learning [0.0]
  We develop a Proximal policy optimization algorithm for queueing networks. The algorithm consistently generates control policies that outperform state-of-arts in literature. A key to the successes of our PPO algorithm is the use of three variance reduction techniques in estimating the relative value function.
  arXiv  Detail & Related papers  (2020-07-31T01:02:57Z)
• FACMAC: Factored Multi-Agent Centralised Policy Gradients [103.30380537282517]
  We propose FACtored Multi-Agent Centralised policy gradients (FACMAC) It is a new method for cooperative multi-agent reinforcement learning in both discrete and continuous action spaces. We evaluate FACMAC on variants of the multi-agent particle environments, a novel multi-agent MuJoCo benchmark, and a challenging set of StarCraft II micromanagement tasks.
  arXiv  Detail & Related papers  (2020-03-14T21:29:09Z)

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.