Applying reinforcement learning to small scale combat in the real-time strategy game StarCraft:Broodwar

By Stefan Wender, Ian D. Watson. 2012

111 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Sociology and Political Science

Citations in the corpus

TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games (2016, background): “Most previous reinforcement learning research involve simple models or limited experimental settings [26, 23].”
Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks (2016, methodology): “This contrast with prior work on Q-learning for micromanagement such as [45], which use features such as the expected inﬂicted damage.”
Heuristic Search Techniques for Real-Time Strategy Games (2016, methodology): “Wender and Watson [89] implemented several different RL algorithms which performed small-scale starcraft combat and found that of the algorithms tested, one-step Q-learning and Sarsa(λ) performed the best.”
Knowledge-Guided Agent-Tactic-Aware Learning for StarCraft Micromanagement (2018, background): “In recent years, StarCraft micromanagement [Ontan´on et al. , 2013; Wender and Watson, 2012; Synnaeve et al. , 2016] based on deep reinforcement learning (DRL) [Mnih et al. , 2015; Li, 2017; Silver et al. , 2016; Lillicrap et al. , 2015; Levine et al. , 2016; Mirowski et al. , 2017; Pasunuru and…”
StarCraft Micromanagement With Reinforcement Learning and Curriculum Transfer Learning (2018, methodology): “Second, we present a parameter sharing multi-agent gradient-descent Sarsa( λ ) (PS-MAGDS) algorithm to train our units.”
An Introduction to Deep Reinforcement Learning (2018, unknown): “Finally, “StarCraft II" (Vinyals et al., 2017) and “Starcraft: Broodwar" (Wender and Watson, 2012; Synnaeve et al., 2016) provide similar benefits in exploring lifelong-learning, curriculum learning, and other related hierarchical approaches.”
Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks (2018, background): “…make the task harder by (i) removing macro-actions making exploration harder (ii) limiting vision making environment partially observable(iii) unlike previous works (Wender & Watson, 2012; Ontanón et al., 2013; Usunier et al., As is evident from (f) , they stop communicating once they reach prey.”
Evolving effective micro behaviors in RTS game (2014, methodology): “Wender et. al. evaluated the suitability of reinforcement learning algorithms to perform the task of micro managing combat units in RTS games [25] .”
A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft (2013, unknown): “Additionally, there have been some interesting uses of reinforcement learning (RL) [51]: Wender and Watson [52] evaluated the different major RL algorithms for (decentralized) micro-management, which perform all equally.”