Policy Distillation and Value Matching in Multiagent Reinforcement Learning

March 15, 2019 ยท Declared Dead ยท ๐Ÿ› IEEE/RJS International Conference on Intelligent RObots and Systems

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Samir Wadhwania, Dong-Ki Kim, Shayegan Omidshafiei, Jonathan P. How arXiv ID 1903.06592 Category cs.LG: Machine Learning Cross-listed cs.AI, stat.ML Citations 32 Venue IEEE/RJS International Conference on Intelligent RObots and Systems Last Checked 4 months ago
Abstract
Multiagent reinforcement learning algorithms (MARL) have been demonstrated on complex tasks that require the coordination of a team of multiple agents to complete. Existing works have focused on sharing information between agents via centralized critics to stabilize learning or through communication to increase performance, but do not generally look at how information can be shared between agents to address the curse of dimensionality in MARL. We posit that a multiagent problem can be decomposed into a multi-task problem where each agent explores a subset of the state space instead of exploring the entire state space. This paper introduces a multiagent actor-critic algorithm and method for combining knowledge from homogeneous agents through distillation and value-matching that outperforms policy distillation alone and allows further learning in both discrete and continuous action spaces.
Community shame:
Not yet rated
Community Contributions

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

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted