A multi-expert action-advice method plus a blockchain model marketplace speeds up multi-agent reinforcement learning under sparse rewards and tolerates faulty experts.
Fault- tolerant federated reinforcement learning with theoretical guarantee,
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 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Blockchain-assisted Demonstration Cloning for Multi-Agent Deep Reinforcement Learning
A multi-expert action-advice method plus a blockchain model marketplace speeds up multi-agent reinforcement learning under sparse rewards and tolerates faulty experts.