Cooperative Multi-Agent Reinforcement Learning with Partial Observations

• URL: http://arxiv.org/abs/2006.10822v2
• Date: Fri, 16 Jun 2023 23:45:07 GMT
• Title: Cooperative Multi-Agent Reinforcement Learning with Partial Observations
• Authors: Yan Zhang, Michael M. Zavlanos
• Abstract summary: We propose a distributed zeroth-order policy optimization method for Multi-Agent Reinforcement Learning (MARL) It allows the agents to compute the local policy gradients needed to update their local policy functions using local estimates of the global accumulated rewards. We show that the proposed distributed zeroth-order policy optimization method with constant stepsize converges to the neighborhood of a policy that is a stationary point of the global objective function.
• Score: 16.895704973433382
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose a distributed zeroth-order policy optimization method for Multi-Agent Reinforcement Learning (MARL). Existing MARL algorithms often assume that every agent can observe the states and actions of all the other agents in the network. This can be impractical in large-scale problems, where sharing the state and action information with multi-hop neighbors may incur significant communication overhead. The advantage of the proposed zeroth-order policy optimization method is that it allows the agents to compute the local policy gradients needed to update their local policy functions using local estimates of the global accumulated rewards that depend on partial state and action information only and can be obtained using consensus. Specifically, to calculate the local policy gradients, we develop a new distributed zeroth-order policy gradient estimator that relies on one-point residual-feedback which, compared to existing zeroth-order estimators that also rely on one-point feedback, significantly reduces the variance of the policy gradient estimates improving, in this way, the learning performance. We show that the proposed distributed zeroth-order policy optimization method with constant stepsize converges to the neighborhood of a policy that is a stationary point of the global objective function. The size of this neighborhood depends on the agents' learning rates, the exploration parameters, and the number of consensus steps used to calculate the local estimates of the global accumulated rewards. Moreover, we provide numerical experiments that demonstrate that our new zeroth-order policy gradient estimator is more sample-efficient compared to other existing one-point estimators.

Related papers

• Networked Communication for Mean-Field Games with Function Approximation and Empirical Mean-Field Estimation [59.01527054553122]
  Decentralised agents can learn equilibria in Mean-Field Games from a single, non-episodic run of the empirical system. We introduce function approximation to the existing setting, drawing on the Munchausen Online Mirror Descent method. We additionally provide new algorithms that allow agents to estimate the global empirical distribution based on a local neighbourhood.
  arXiv  Detail & Related papers  (2024-08-21T13:32:46Z)
• Score-Aware Policy-Gradient Methods and Performance Guarantees using Local Lyapunov Conditions: Applications to Product-Form Stochastic Networks and Queueing Systems [1.747623282473278]
  We introduce a policygradient method for model reinforcement learning (RL) that exploits a type of stationary distributions commonly obtained from decision processes (MDPs) in networks. Specifically, when the stationary distribution of the MDP is parametrized by policy parameters, we can improve existing policy methods for average-reward estimation.
  arXiv  Detail & Related papers  (2023-12-05T14:44:58Z)
• Off-Policy Evaluation for Large Action Spaces via Policy Convolution [60.6953713877886]
  Policy Convolution family of estimators uses latent structure within actions to strategically convolve the logging and target policies. Experiments on synthetic and benchmark datasets demonstrate remarkable mean squared error (MSE) improvements when using PC.
  arXiv  Detail & Related papers  (2023-10-24T01:00:01Z)
• Provable Offline Preference-Based Reinforcement Learning [95.00042541409901]
  We investigate the problem of offline Preference-based Reinforcement Learning (PbRL) with human feedback. We consider the general reward setting where the reward can be defined over the whole trajectory. We introduce a new single-policy concentrability coefficient, which can be upper bounded by the per-trajectory concentrability.
  arXiv  Detail & Related papers  (2023-05-24T07:11:26Z)
• 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)
• Decentralized Multi-Agent Reinforcement Learning: An Off-Policy Method [6.261762915564555]
  We discuss the problem of decentralized multi-agent reinforcement learning (MARL) in this work. In our setting, the global state, action, and reward are assumed to be fully observable, while the local policy is protected as privacy by each agent, and thus cannot be shared with others. The policy evaluation and policy improvement algorithms are designed for discrete and continuous state-action-space Markov Decision Process (MDP) respectively.
  arXiv  Detail & Related papers  (2021-10-31T09:08:46Z)
• 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)
• Multi-Agent Trust Region Policy Optimization [34.91180300856614]
  We show that the policy update of TRPO can be transformed into a distributed consensus optimization problem for multi-agent cases. We propose a decentralized MARL algorithm, which we call multi-agent TRPO (MATRPO)
  arXiv  Detail & Related papers  (2020-10-15T17:49:47Z)
• Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation [49.502277468627035]
  This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history.
  arXiv  Detail & Related papers  (2020-02-21T19:20:57Z)
• Kalman meets Bellman: Improving Policy Evaluation through Value Tracking [59.691919635037216]
  Policy evaluation is a key process in Reinforcement Learning (RL) We devise an optimization method, called Kalman Optimization for Value Approximation (KOVA) KOVA minimizes a regularized objective function that concerns both parameter and noisy return uncertainties.
  arXiv  Detail & Related papers  (2020-02-17T13:30:43Z)

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.