arXiv subjects

Zhenkun Tang

Publications and source records attributed to Zhenkun Tang.

3 recordsLinked to original sources

arXiv2020

SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II

AlphaStar, the AI that reaches GrandMaster level in StarCraft II, is a remarkable milestone demonstrating what deep reinforcement learning can achieve in complex Real-Time Strategy (RTS) games. However, the complexities of the game, algorithms and systems, and especially the tremendous amount of computation needed are big obstacles for the community to conduct further research in this direction. We propose a deep reinforcement learning agent, StarCraft Commander (SCC). With order of magnitude less computation, it demonstrates top human performance defeating GrandMaster players in test matches and top professional players in a live event. Moreover, it shows strong robustness to various human strategies and discovers novel strategies unseen from human plays. In this paper, we will share the key insights and optimizations on efficient imitation learning and reinforcement learning for StarCraft II full game.

cs.LG↗

arXiv2019

Selective control of localised vs. delocalised carriers in anatase TiO2 through reaction with O2

Two-dimensional (2D) metallic states induced by oxygen vacancies at oxide surfaces and interfaces provide new opportunities for the development of advanced applications, but the ability to control the behavior of these states is still limited. We used Angle Resolved Photoelectron Spectroscopy combined with density functional theory to study the reactivity of states induced by the oxygen vacancies at the (001)-(1x4) surface of anatase TiO2, where both 2D metallic and deeper lying in-gap states (IGs) are observed. Remarkably, the two states exhibit very different evolution when the surface is exposed to molecular O2: while IGs are almost completely quenched, the metallic states are only weakly affected. The energy scale analysis for the vacancy migration and recombination resulting from the DFT calculations confirms indeed that only the IGs originate from and remain localized at the surface, whereas the metallic states originate from subsurface vacancies, whose migration and recombination at the surface is energetically less favorable rendering them therefore insensitive to oxygen dosing.

cond-mat.mtrl-sci↗

arXiv2017

Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games

Many artificial intelligence (AI) applications often require multiple intelligent agents to work in a collaborative effort. Efficient learning for intra-agent communication and coordination is an indispensable step towards general AI. In this paper, we take StarCraft combat game as a case study, where the task is to coordinate multiple agents as a team to defeat their enemies. To maintain a scalable yet effective communication protocol, we introduce a Multiagent Bidirectionally-Coordinated Network (BiCNet ['bIknet]) with a vectorised extension of actor-critic formulation. We show that BiCNet can handle different types of combats with arbitrary numbers of AI agents for both sides. Our analysis demonstrates that without any supervisions such as human demonstrations or labelled data, BiCNet could learn various types of advanced coordination strategies that have been commonly used by experienced game players. In our experiments, we evaluate our approach against multiple baselines under different scenarios; it shows state-of-the-art performance, and possesses potential values for large-scale real-world applications.

cs.AI↗