Pith. sign in

REVIEW 4 cited by

V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2110.14555 v1 pith:3ZI67ZN3 submitted 2021-10-27 cs.LG cs.AIcs.GTcs.MAstat.ML

classification cs.LGcs.AIcs.GTcs.MAstat.ML
keywords v-learningalgorithmalgorithmsequilibriamarlnumbersettingaction
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

A major challenge of multiagent reinforcement learning (MARL) is the curse of multiagents, where the size of the joint action space scales exponentially with the number of agents. This remains to be a bottleneck for designing efficient MARL algorithms even in a basic scenario with finitely many states and actions. This paper resolves this challenge for the model of episodic Markov games. We design a new class of fully decentralized algorithms -- V-learning, which provably learns Nash equilibria (in the two-player zero-sum setting), correlated equilibria and coarse correlated equilibria (in the multiplayer general-sum setting) in a number of samples that only scales with $\max_{i\in[m]} A_i$, where $A_i$ is the number of actions for the $i^{\rm th}$ player. This is in sharp contrast to the size of the joint action space which is $\prod_{i=1}^m A_i$. V-learning (in its basic form) is a new class of single-agent RL algorithms that convert any adversarial bandit algorithm with suitable regret guarantees into a RL algorithm. Similar to the classical Q-learning algorithm, it performs incremental updates to the value functions. Different from Q-learning, it only maintains the estimates of V-values instead of Q-values. This key difference allows V-learning to achieve the claimed guarantees in the MARL setting by simply letting all agents run V-learning independently.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. PAC Learning in Turn-Based Stochastic Games with Reachability Objectives: A Decentralized Private Approach via Expected Conditional Distance

    cs.LG 2026-07 conditional novelty 7.0 of 10

    A decentralized, private-information PAC-learning algorithm exists for reachability in turn-based stochastic games whenever the expected conditional distance to the target is bounded.

  2. Solving Zero-Sum Convex Markov Games

    cs.GT 2025-06 conditional novelty 7.0 of 10

    Independent policy-gradient algorithms provably compute approximate Nash equilibria in two-player zero-sum convex Markov games.

  3. Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games

    cs.LG 2025-02 conditional novelty 6.0 of 10

    Value-incentivized exploration via best-response values gives near-optimal regret for NE/CCE in linear-model Markov games without explicit uncertainty bonuses.

  4. Reinforcement Learning on Dyads to Enhance Medication Adherence

    cs.LG 2025-02 conditional novelty 5.0 of 10

    A three-agent reinforcement learning framework with domain-informed surrogate rewards outperforms single-agent and random policies for personalizing dyadic medication-adherence interventions in simulation.

Pith tools