Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspective

• URL: http://arxiv.org/abs/2403.11345v1
• Date: Sun, 17 Mar 2024 21:11:55 GMT
• Title: Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspective
• Authors: Muhammad Aneeq uz Zaman, Alec Koppel, Mathieu Laurière, Tamer Başar,
• Abstract summary: We address in this paper Reinforcement Learning (RL) among agents that are grouped into teams such that there is cooperation within each team but general-sum competition across different teams.
• Score: 11.603515105957461
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We address in this paper Reinforcement Learning (RL) among agents that are grouped into teams such that there is cooperation within each team but general-sum (non-zero sum) competition across different teams. To develop an RL method that provably achieves a Nash equilibrium, we focus on a linear-quadratic structure. Moreover, to tackle the non-stationarity induced by multi-agent interactions in the finite population setting, we consider the case where the number of agents within each team is infinite, i.e., the mean-field setting. This results in a General-Sum LQ Mean-Field Type Game (GS-MFTGs). We characterize the Nash equilibrium (NE) of the GS-MFTG, under a standard invertibility condition. This MFTG NE is then shown to be $\mathcal{O}(1/M)$-NE for the finite population game where $M$ is a lower bound on the number of agents in each team. These structural results motivate an algorithm called Multi-player Receding-horizon Natural Policy Gradient (MRPG), where each team minimizes its cumulative cost independently in a receding-horizon manner. Despite the non-convexity of the problem, we establish that the resulting algorithm converges to a global NE through a novel problem decomposition into sub-problems using backward recursive discrete-time Hamilton-Jacobi-Isaacs (HJI) equations, in which independent natural policy gradient is shown to exhibit linear convergence under time-independent diagonal dominance. Experiments illuminate the merits of this approach in practice.

Related papers

• Linear Convergence of Independent Natural Policy Gradient in Games with Entropy Regularization [12.612009339150504]
  This work focuses on the entropy-regularized independent natural policy gradient (NPG) algorithm in multi-agent reinforcement learning. We show that, under sufficient entropy regularization, the dynamics of this system converge at a linear rate to the quantal response equilibrium (QRE)
  arXiv  Detail & Related papers  (2024-05-04T22:48:53Z)
• MF-OML: Online Mean-Field Reinforcement Learning with Occupation Measures for Large Population Games [5.778024594615575]
  This paper proposes an online mean-field reinforcement learning algorithm for computing Nash equilibria of sequential games. MFOML is the first fully approximate multi-agent reinforcement learning algorithm for provably solving Nash equilibria. As a byproduct, we also obtain the first tractable globally convergent computational for approximate computing of monotone mean-field games.
  arXiv  Detail & Related papers  (2024-05-01T02:19:31Z)
• Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence Beyond the Minty Property [89.96815099996132]
  We develop a new framework to characterize optimistic policy gradient methods in multi-player games with a single controller. Our approach relies on a natural generalization of the classical Minty property that we introduce, which we anticipate to have further applications beyond Markov games.
  arXiv  Detail & Related papers  (2023-12-19T11:34:10Z)
• Global Nash Equilibrium in Non-convex Multi-player Game: Theory and Algorithms [66.8634598612777]
  We show that Nash equilibrium (NE) is acceptable to all players in a multi-player game. We also show that no one can benefit unilaterally from the general theory step by step.
  arXiv  Detail & Related papers  (2023-01-19T11:36:50Z)
• Minimax-Optimal Multi-Agent RL in Zero-Sum Markov Games With a Generative Model [50.38446482252857]
  Two-player zero-sum Markov games are arguably the most basic setting in multi-agent reinforcement learning. We develop a learning algorithm that learns an $varepsilon$-approximate Markov NE policy using $$ widetildeObigg. We derive a refined regret bound for FTRL that makes explicit the role of variance-type quantities.
  arXiv  Detail & Related papers  (2022-08-22T17:24:55Z)
• Optimal Clustering with Bandit Feedback [57.672609011609886]
  This paper considers the problem of online clustering with bandit feedback. It includes a novel stopping rule for sequential testing that circumvents the need to solve any NP-hard weighted clustering problem as its subroutines. We show through extensive simulations on synthetic and real-world datasets that BOC's performance matches the lower boundally, and significantly outperforms a non-adaptive baseline algorithm.
  arXiv  Detail & Related papers  (2022-02-09T06:05:05Z)
• Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence [30.084357461497042]
  We learn a Nash equilibrium of an MPG in which the size of state space and/or the number of players can be very large. We propose new independent policy gradient algorithms that are run by all players in tandem. We identify a class of independent policy gradient algorithms that enjoys convergence for both zero-sum Markov games and Markov cooperative games with the players that are oblivious to the types of games being played.
  arXiv  Detail & Related papers  (2022-02-08T20:09:47Z)
• Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games [104.74734408204749]
  We show that if all agents in a multi-player general-sum normal-form game employ Optimistic Multiplicative Weights Update (OMWU), the external regret of every player is $O(textrmpolylog(T))$ after $T$ repetitions of the game. We extend their result from external regret to internal regret and swap regret, thereby establishing uncoupled learning dynamics that converge to an approximate correlated equilibrium.
  arXiv  Detail & Related papers  (2021-11-11T01:19:53Z)
• Reinforcement Learning in Non-Stationary Discrete-Time Linear-Quadratic Mean-Field Games [14.209473797379667]
  We study large population multi-agent reinforcement learning (RL) in the context of discrete-time linear-quadratic mean-field games (LQ-MFGs) Our setting differs from most existing work on RL for MFGs, in that we consider a non-stationary MFG over an infinite horizon. We propose an actor-critic algorithm to iteratively compute the mean-field equilibrium (MFE) of the LQ-MFG.
  arXiv  Detail & Related papers  (2020-09-09T15:17:52Z)
• Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity [67.02490430380415]
  We show that model-based MARL achieves a sample complexity of $tilde O(|S||B|(gamma)-3epsilon-2)$ for finding the Nash equilibrium (NE) value up to some $epsilon$ error. We also show that such a sample bound is minimax-optimal (up to logarithmic factors) if the algorithm is reward-agnostic, where the algorithm queries state transition samples without reward knowledge.
  arXiv  Detail & Related papers  (2020-07-15T03:25:24Z)

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.