Abstract:We study cooperative multi-agent reinforcement learning in the setting of reward-free exploration, where multiple agents jointly explore an unknown MDP in order to learn its dynamics (without observing rewards). We focus on a tabular finite-horizon MDP and adopt a phased learning framework. In each learning phase, multiple agents independently interact with the environment. More specifically, in each learning phase, each agent is assigned a policy, executes it, and observes the resulting trajectory. Our primary goal is to characterize the tradeoff between the number of learning phases and the number of agents, especially when the number of learning phases is small.
Our results identify a regime change governed by the horizon $H$. When the number of learning phases equals $H$, we present a computationally efficient algorithm that uses only $\tilde{O}(S^6 H^6 A / \epsilon^2)$ agents to obtain an $\epsilon$ approximation of the dynamics (i.e., yields an $\epsilon$-optimal policy for any reward function). We complement our algorithm with a lower bound showing that any algorithm restricted to $\rho < H$ phases requires at least $A^{H/\rho}$ agents to achieve constant accuracy. Thus, we show that having $\Theta(H)$ learning phases is both necessary and sufficient when restricting the number of agents to be polynomial.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2602.01453 [cs.LG] |
| (or arXiv:2602.01453v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2602.01453 arXiv-issued DOI via DataCite |
From: Idan Barnea [view email]
[v1]
Sun, 1 Feb 2026 21:44:11 UTC (68 KB)
[v2]
Sat, 7 Feb 2026 18:47:34 UTC (68 KB)
[v3]
Wed, 13 May 2026 08:02:45 UTC (46 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。