Bayesian Reinforcement Learning in Factored POMDPs

November 14, 2018 Β· Declared Dead Β· πŸ› Adaptive Agents and Multi-Agent 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 Sammie Katt, Frans Oliehoek, Christopher Amato arXiv ID 1811.05612 Category cs.AI: Artificial Intelligence Citations 42 Venue Adaptive Agents and Multi-Agent Systems Last Checked 4 months ago
Abstract
Bayesian approaches provide a principled solution to the exploration-exploitation trade-off in Reinforcement Learning. Typical approaches, however, either assume a fully observable environment or scale poorly. This work introduces the Factored Bayes-Adaptive POMDP model, a framework that is able to exploit the underlying structure while learning the dynamics in partially observable systems. We also present a belief tracking method to approximate the joint posterior over state and model variables, and an adaptation of the Monte-Carlo Tree Search solution method, which together are capable of solving the underlying problem near-optimally. Our method is able to learn efficiently given a known factorization or also learn the factorization and the model parameters at the same time. We demonstrate that this approach is able to outperform current methods and tackle problems that were previously infeasible.
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