Policy Gradient With Value Function Approximation For Collective Multiagent Planning

April 09, 2018 Β· Declared Dead Β· πŸ› Neural Information Processing Systems

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Duc Thien Nguyen, Akshat Kumar, Hoong Chuin Lau arXiv ID 1804.02884 Category cs.AI: Artificial Intelligence Cross-listed cs.LG, cs.MA, cs.NE, eess.SY Citations 46 Venue Neural Information Processing Systems Last Checked 3 months ago
Abstract
Decentralized (PO)MDPs provide an expressive framework for sequential decision making in a multiagent system. Given their computational complexity, recent research has focused on tractable yet practical subclasses of Dec-POMDPs. We address such a subclass called CDEC-POMDP where the collective behavior of a population of agents affects the joint-reward and environment dynamics. Our main contribution is an actor-critic (AC) reinforcement learning method for optimizing CDEC-POMDP policies. Vanilla AC has slow convergence for larger problems. To address this, we show how a particular decomposition of the approximate action-value function over agents leads to effective updates, and also derive a new way to train the critic based on local reward signals. Comparisons on a synthetic benchmark and a real-world taxi fleet optimization problem show that our new AC approach provides better quality solutions than previous best approaches.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ‘» Ghosted