method · first seen 8 Oct 2026
federated temporal difference learning
Collaborative reinforcement learning in which agents share updates to estimate value functions under heterogeneity.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Best of Both Worlds in Federated LSA: Speedup When Possible, Personalization AlwaysPapers · 8 Oct 2026 · Safwan Labbi, Paul Mangold, Eric Moulines
Latest sources
- Best of Both Worlds in Federated LSA: Speedup When Possible, Personalization AlwaysPapers · 8 Oct 2026 · Safwan Labbi, Paul Mangold, Eric Moulines