paper-with-me

Papers

Combinatorial Multi-armed Bandits for Real-Time Strategy Games

2017-10-13 · Santiago Ontañón

Games with large branching factors pose a significant challenge for game tree search algorithms. In this paper, we address this problem with a sampling strategy for Monte Carlo Tree Search (MCTS) algorithms called {\em na\"{i}ve sampling}, based on a variant of the Multi-armed Bandit problem called {\em Combinatorial Multi-armed Bandits} (CMAB). We analyze the theoretical properties of several variants of {\em na\"{i}ve sampling}, and empirically compare it against the other existing strategies in the literature for CMABs. We then evaluate these strategies in the context of real-time strategy (RTS) games, a genre of computer games characterized by their very large branching factors. Our results show that as the branching factor grows, {\em na\"{i}ve sampling} outperforms the other sampling strategies.

📄 PDF Abstract BibTeX arXiv:1710.04805

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed BanditsReal-Time Strategy Games

Similar Papers 제목 키워드 기반

Combinatorial Semi-Bandits with Knapsacks

2017-05-23 · Karthik Abinav Sankararaman, Aleksandrs Slivkins

We unify two prominent lines of work on multi-armed bandits: bandits with knapsacks (BwK) and combinatorial semi-bandits. The former concerns limited "resources" consumed by the algorithm, e.g., limited supply in dynamic…

Multi-Armed Bandits

Adversarial Attacks on Combinatorial Multi-Armed Bandits

2023-10-08 · Rishab Balasubramanian, Jiawei Li, Prasad Tadepalli, Huazheng Wang 외

We study reward poisoning attacks on Combinatorial Multi-armed Bandits (CMAB). We first provide a sufficient and necessary condition for the attackability of CMAB, a notion to capture the vulnerability and robustness of …

Multi-Armed Bandits

A Fast Algorithm for the Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit

2023-06-15 · Shintaro Nakamura, Masashi Sugiyama

We study the real-valued combinatorial pure exploration problem in the stochastic multi-armed bandit (R-CPE-MAB). We study the case where the size of the action set is polynomial with respect to the number of arms. In su…

Decision Making

Master-slave Deep Architecture for Top-K Multi-armed Bandits with Non-linear Bandit Feedback and Diversity Constraints

2023-08-24 · Hanchi Huang, Li Shen, Deheng Ye, Wei Liu

We propose a novel master-slave architecture to solve the top-$K$ combinatorial multi-armed bandits problem with non-linear bandit feedback and diversity constraints, which, to the best of our knowledge, is the first com…

DiversityMulti-Armed Bandits

Tight Lower Bounds for Combinatorial Multi-Armed Bandits

2020-02-13 · Nadav Merlis, Shie Mannor

The Combinatorial Multi-Armed Bandit problem is a sequential decision-making problem in which an agent selects a set of arms on each round, observes feedback for each of these arms and aims to maximize a known reward fun…

Decision MakingMulti-Armed BanditsSequential Decision Making