Pith. sign in

REVIEW 1 cited by

Finite-Sample Analysis of Decentralized Q-Learning for Stochastic Games

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 2112.07859 v2 pith:Q74FXGJ6 submitted 2021-12-15 cs.GT cs.LGcs.MA

classification cs.GTcs.LGcs.MA
keywords decentralizedequilibriumgameslinearmarlsettingstochasticagent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Learning in stochastic games is arguably the most standard and fundamental setting in multi-agent reinforcement learning (MARL). In this paper, we consider decentralized MARL in stochastic games in the non-asymptotic regime. In particular, we establish the finite-sample complexity of fully decentralized Q-learning algorithms in a significant class of general-sum stochastic games (SGs) - weakly acyclic SGs, which includes the common cooperative MARL setting with an identical reward to all agents (a Markov team problem) as a special case. We focus on the practical while challenging setting of fully decentralized MARL, where neither the rewards nor the actions of other agents can be observed by each agent. In fact, each agent is completely oblivious to the presence of other decision makers. Both the tabular and the linear function approximation cases have been considered. In the tabular setting, we analyze the sample complexity for the decentralized Q-learning algorithm to converge to a Markov perfect equilibrium (Nash equilibrium). With linear function approximation, the results are for convergence to a linear approximated equilibrium - a new notion of equilibrium that we propose - which describes that each agent's policy is a best reply (to other agents) within a linear space. Numerical experiments are also provided for both settings to demonstrate the results.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Equilibrium stability as a driver of cooperation among Q-learners

    cs.MA 2026-07 conditional novelty 6.0 of 10

    Q-learners with constant exploration in the repeated prisoner's dilemma spend most of their time on cooperative win-stay/lose-shift play above a boundary derived from Q-value gaps, matching simulations.

Pith tools