Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies

• URL: http://arxiv.org/abs/2508.01049v1
• Date: Fri, 01 Aug 2025 20:07:25 GMT
• Title: Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies
• Authors: Nicholas E. Corrado, Josiah P. Hanna,
• Abstract summary: Independent on-policy policy gradient algorithms are widely used for multi-agent reinforcement learning (MARL) in cooperative and no-conflict games.<n>They are known to converge suboptimally when each agent's policy gradient points toward a suboptimal equilibrium.<n>We introduce an adaptive action sampling approach to reduce joint sampling error.
• Score: 3.5253513747455303
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Independent on-policy policy gradient algorithms are widely used for multi-agent reinforcement learning (MARL) in cooperative and no-conflict games, but they are known to converge suboptimally when each agent's policy gradient points toward a suboptimal equilibrium. In this work, we identify a subtler failure mode that arises \textit{even when the expected policy gradients of all agents point toward an optimal solution.} After collecting a finite set of trajectories, stochasticity in independent action sampling can cause the joint data distribution to deviate from the expected joint on-policy distribution. This \textit{sampling error} w.r.t. the joint on-policy distribution produces inaccurate gradient estimates that can lead agents to converge suboptimally. In this paper, we investigate if joint sampling error can be reduced through coordinated action selection and whether doing so improves the reliability of policy gradient learning in MARL. Toward this end, we introduce an adaptive action sampling approach to reduce joint sampling error. Our method, Multi-Agent Proximal Robust On-Policy Sampling (MA-PROPS), uses a centralized behavior policy that we continually adapt to place larger probability on joint actions that are currently under-sampled w.r.t. the current joint policy. We empirically evaluate MA-PROPS in a diverse range of multi-agent games and demonstrate that (1) MA-PROPS reduces joint sampling error more efficiently than standard on-policy sampling and (2) improves the reliability of independent policy gradient algorithms, increasing the fraction of training runs that converge to an optimal joint policy.

Related papers

• Offline Multi-agent Reinforcement Learning via Score Decomposition [51.23590397383217]
  offline cooperative multi-agent reinforcement learning (MARL) faces unique challenges due to distributional shifts.<n>This work is the first work to explicitly address the distributional gap between offline and online MARL.
  arXiv  Detail & Related papers  (2025-05-09T11:42:31Z)
• Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization [8.877649895977479]
  offline Multi-Agent Reinforcement Learning (MARL) is an emerging field that aims to learn optimal multi-agent policies from pre-collected datasets.<n>In this work, we revisit the existing offline MARL methods and show that in certain scenarios they can be problematic.<n>We propose a new offline MARL algorithm, named In-Sample Sequential Policy Optimization (InSPO)
  arXiv  Detail & Related papers  (2024-12-10T16:19:08Z)
• Simulation-Based Optimistic Policy Iteration For Multi-Agent MDPs with Kullback-Leibler Control Cost [3.9052860539161918]
  This paper proposes an agent-based optimistic policy (OPI) scheme for learning stationary optimal policies in Markov Decision Processes (MDPs) The proposed scheme consists of a greedy policy improvement step followed by an m-step temporal difference (TD) policy evaluation step. We show that both the synchronous (entire state space evaluation) and asynchronous (a uniformly sampled set of substates) versions of the OPI scheme converge to the optimal value function and an optimal joint policy rollout.
  arXiv  Detail & Related papers  (2024-10-19T17:00:23Z)
• 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)
• Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement Learning [7.4447396913959185]
  This paper studies a distributed policy gradient in collaborative multi-agent reinforcement learning (MARL) Agents over a communication network aim to find the optimal policy to maximize the average of all agents' local returns.
  arXiv  Detail & Related papers  (2021-11-25T08:07:30Z)
• 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)
• Dealing with Non-Stationarity in Multi-Agent Reinforcement Learning via Trust Region Decomposition [52.06086375833474]
  Non-stationarity is one thorny issue in multi-agent reinforcement learning. We introduce a $delta$-stationarity measurement to explicitly model the stationarity of a policy sequence. We propose a trust region decomposition network based on message passing to estimate the joint policy divergence.
  arXiv  Detail & Related papers  (2021-02-21T14:46:50Z)
• Improper Learning with Gradient-based Policy Optimization [62.50997487685586]
  We consider an improper reinforcement learning setting where the learner is given M base controllers for an unknown Markov Decision Process. We propose a gradient-based approach that operates over a class of improper mixtures of the controllers.
  arXiv  Detail & Related papers  (2021-02-16T14:53:55Z)
• Implicit Distributional Reinforcement Learning [61.166030238490634]
  implicit distributional actor-critic (IDAC) built on two deep generator networks (DGNs) Semi-implicit actor (SIA) powered by a flexible policy distribution. We observe IDAC outperforms state-of-the-art algorithms on representative OpenAI Gym environments.
  arXiv  Detail & Related papers  (2020-07-13T02:52:18Z)
• Variational Policy Propagation for Multi-agent Reinforcement Learning [68.26579560607597]
  We propose a emphcollaborative multi-agent reinforcement learning algorithm named variational policy propagation (VPP) to learn a emphjoint policy through the interactions over agents. We prove that the joint policy is a Markov Random Field under some mild conditions, which in turn reduces the policy space effectively. We integrate the variational inference as special differentiable layers in policy such as the actions can be efficiently sampled from the Markov Random Field and the overall policy is differentiable.
  arXiv  Detail & Related papers  (2020-04-19T15:42:55Z)

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.