Linear-Quadratic Mean-Field Reinforcement Learning: Convergence of Policy Gradient Methods

• URL: http://arxiv.org/abs/1910.04295v2
• Date: Mon, 28 Apr 2025 23:55:02 GMT
• Title: Linear-Quadratic Mean-Field Reinforcement Learning: Convergence of Policy Gradient Methods
• Authors: René Carmona, Mathieu Laurière, Zongjun Tan,
• Abstract summary: We investigate reinforcement learning in the setting of Markov decision processes for a large number of exchangeable agents interacting in a mean field manner.<n>An approximate solution is obtained by learning the optimal policy of a generic agent interacting with the statistical distribution of the states and actions of the other agents.
• Score: 2.330509865741341
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We investigate reinforcement learning in the setting of Markov decision processes for a large number of exchangeable agents interacting in a mean field manner. Applications include, for example, the control of a large number of robots communicating through a central unit dispatching the optimal policy computed by maximizing an aggregate reward. An approximate solution is obtained by learning the optimal policy of a generic agent interacting with the statistical distribution of the states and actions of the other agents. We first provide a full analysis this discrete-time mean field control problem. We then rigorously prove the convergence of exact and model-free policy gradient methods in a mean-field linear-quadratic setting and establish bounds on the rates of convergence. We also provide graphical evidence of the convergence based on implementations of our algorithms.

Related papers

• Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems [61.580419063416734]
  A recent stream of structured learning approaches has improved the practical state of the art for a range of optimization problems. The key idea is to exploit the statistical distribution over instances instead of dealing with instances separately. In this article, we investigate methods that smooth the risk by perturbing the policy, which eases optimization and improves the generalization error.
  arXiv  Detail & Related papers  (2024-07-24T12:00:30Z)
• Learning Optimal Deterministic Policies with Stochastic Policy Gradients [62.81324245896716]
  Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. In common practice, convergence (hyper)policies are learned only to deploy their deterministic version. We show how to tune the exploration level used for learning to optimize the trade-off between the sample complexity and the performance of the deployed deterministic policy.
  arXiv  Detail & Related papers  (2024-05-03T16:45:15Z)
• Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning [46.28771270378047]
  Federated reinforcement learning (RL) enables collaborative decision making of multiple distributed agents without sharing local data trajectories. In this work, we consider a multi-task setting, in which each agent has its own private reward function corresponding to different tasks, while sharing the same transition kernel of the environment. We learn a globally optimal policy that maximizes the sum of the discounted total rewards of all the agents in a decentralized manner.
  arXiv  Detail & Related papers  (2023-11-01T00:15:18Z)
• High-probability sample complexities for policy evaluation with linear function approximation [88.87036653258977]
  We investigate the sample complexities required to guarantee a predefined estimation error of the best linear coefficients for two widely-used policy evaluation algorithms. We establish the first sample complexity bound with high-probability convergence guarantee that attains the optimal dependence on the tolerance level.
  arXiv  Detail & Related papers  (2023-05-30T12:58:39Z)
• 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)
• Federated Learning for Heterogeneous Bandits with Unobserved Contexts [0.0]
  We study the problem of federated multi-arm contextual bandits with unknown contexts. We propose an elimination-based algorithm and prove the regret bound for linearly parametrized reward functions.
  arXiv  Detail & Related papers  (2023-03-29T22:06:24Z)
• 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)
• Dimension-Free Rates for Natural Policy Gradient in Multi-Agent Reinforcement Learning [22.310861786709538]
  We propose a scalable algorithm for cooperative multi-agent reinforcement learning. We show that our algorithm converges to the globally optimal policy with a dimension-free statistical and computational complexity.
  arXiv  Detail & Related papers  (2021-09-23T23:38:15Z)
• Approximate Midpoint Policy Iteration for Linear Quadratic Control [1.0312968200748118]
  We present a midpoint policy iteration algorithm to solve linear quadratic optimal control problems in both model-based and model-free settings. We show that in the model-based setting it achieves cubic convergence, which is superior to standard policy iteration and policy algorithms that achieve quadratic and linear convergence.
  arXiv  Detail & Related papers  (2020-11-28T20:22:10Z)
• Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous Time [109.06623773924737]
  We study the policy gradient method for the linear-quadratic mean-field control and game. We show that it converges to the optimal solution at a linear rate, which is verified by a synthetic simulation.
  arXiv  Detail & Related papers  (2020-08-16T06:34:11Z)
• A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms [67.67377846416106]
  We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We show that value-based methods such as TD($lambda$) and $Q$-Learning have update rules which are contractive in the space of distributions of functions.
  arXiv  Detail & Related papers  (2020-03-27T05:13:29Z)

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.