BWhat changed
Presented a multi-agent actor-critic method using centralized critics during training and decentralized policies at execution, evaluated in cooperative, competitive and mixed environments.
Scientific scope
The record is the exact NIPS 2017 six-author paper. Single-agent DDPG, Contract Net, self-play, later value-decomposition methods and real-world multi-agent deployment claims remain separate.
Evidence
The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact NIPS 2017 six-author paper. Single-agent DDPG, Contract Net, self-play, later value-decomposition methods and real-world multi-agent deployment claims remain separate.
Contributors
- Ryan Lowe · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
- Yi Wu · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
- Aviv Tamar · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
- Jean Harb · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
- Pieter Abbeel · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
- Igor Mordatch · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction