Adaptive per-agent KL-threshold allocation via KKT (HATRPO-W) and greedy (HATRPO-G) improves HATRPO's final reward by over 22.5% in MARL benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-Agent Trust Region Policy Optimisation: A Joint Constraint Approach
Adaptive per-agent KL-threshold allocation via KKT (HATRPO-W) and greedy (HATRPO-G) improves HATRPO's final reward by over 22.5% in MARL benchmarks.