Skip to content
conftrace_

reference-advantage decomposition

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

variance reduction (2) variance information (1) policy switching cost (1) variance estimators (1) risk sensitive (1) gap-dependent bound (1) policy switching (1) federated q-learning (1) zero-sum markov game (1) entropic risk measure (1)

Papers

Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost ICLR 2025 Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition ICLR 2025 Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games ICML 2024 Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning ICML 2024