Learning Self-Game-Play Agents for Combinatorial Optimization Problems

March 08, 2019 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 Ruiyang Xu, Karl Lieberherr arXiv ID 1903.03674 Category cs.AI: Artificial Intelligence Cross-listed cs.LG Citations 12 Venue Adaptive Agents and Multi-Agent Systems Last Checked 4 months ago
Abstract
Recent progress in reinforcement learning (RL) using self-game-play has shown remarkable performance on several board games (e.g., Chess and Go) as well as video games (e.g., Atari games and Dota2). It is plausible to consider that RL, starting from zero knowledge, might be able to gradually approximate a winning strategy after a certain amount of training. In this paper, we explore neural Monte-Carlo-Tree-Search (neural MCTS), an RL algorithm which has been applied successfully by DeepMind to play Go and Chess at a super-human level. We try to leverage the computational power of neural MCTS to solve a class of combinatorial optimization problems. Following the idea of Hintikka's Game-Theoretical Semantics, we propose the Zermelo Gamification (ZG) to transform specific combinatorial optimization problems into Zermelo games whose winning strategies correspond to the solutions of the original optimization problem. The ZG also provides a specially designed neural MCTS. We use a combinatorial planning problem for which the ground-truth policy is efficiently computable to demonstrate that ZG is promising.
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