HySTAR extends the MAPPO algorithm by separating the credit-assignment topology from the content of agent interactions.
Anchored hypergraphs provide stable credit assignment for multi-agent teams
HySTAR separates adaptive representation learning from a fixed decomposition scaffold, achieving gains on challenging benchmarks.
Industry
Xinglong Luo · Yuding Zhang · Yuheng Kuang · Shuxuan Yuan · Zhenni Zeng · Weiqiang Zhu · +2 more
University of Electronic Science and Technology of China · Independent Researcher
Research Digest··3 min read
The authors introduce HySTAR, a MAPPO-based framework that uses an anchored overlapping sparse hypergraph as a temporally consistent value-decomposition basis, while adapting representations via a spatiotemporal encoder.
Why this paper
From University of Electronic Science and Technology of China and Independent Researcher · Part of Credit Assignment in Agentic RL, now 20 papers
In one line
HySTAR anchors a hypergraph to stabilize credit assignment in cooperative multi-agent RL, improving performance across benchmarks.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks (2 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§