Pith. sign in

Markov games as a framework for multi-age nt reinforcement learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2024 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

Minimax-Optimal Multi-Agent Robust Reinforcement Learning

cs.LG · 2024-12-27 · conditional · novelty 6.0

Robust Q-FTRL achieves ε-robust CCE in R-contaminated Markov games with H^3 S Σ_i A_i min{H,1/R}/ε^2 samples up to logs, matching a new lower bound; two-player zero-sum gives NE.

citing papers explorer

Showing 1 of 1 citing paper.

  • Minimax-Optimal Multi-Agent Robust Reinforcement Learning cs.LG · 2024-12-27 · conditional · none · ref 10

    Robust Q-FTRL achieves ε-robust CCE in R-contaminated Markov games with H^3 S Σ_i A_i min{H,1/R}/ε^2 samples up to logs, matching a new lower bound; two-player zero-sum gives NE.