pith. sign in

On Reinforcement Learning for Full-length Game of StarCraft

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it
abstract

StarCraft II poses a grand challenge for reinforcement learning. The main difficulties of it include huge state and action space and a long-time horizon. In this paper, we investigate a hierarchical reinforcement learning approach for StarCraft II. The hierarchy involves two levels of abstraction. One is the macro-action automatically extracted from expert's trajectories, which reduces the action space in an order of magnitude yet remains effective. The other is a two-layer hierarchical architecture which is modular and easy to scale, enabling a curriculum transferring from simpler tasks to more complex tasks. The reinforcement training algorithm for this architecture is also investigated. On a 64x64 map and using restrictive units, we achieve a winning rate of more than 99\% against the difficulty level-1 built-in AI. Through the curriculum transfer learning algorithm and a mixture of combat model, we can achieve over 93\% winning rate of Protoss against the most difficult non-cheating built-in AI (level-7) of Terran, training within two days using a single machine with only 48 CPU cores and 8 K40 GPUs. It also shows strong generalization performance, when tested against never seen opponents including cheating levels built-in AI and all levels of Zerg and Protoss built-in AI. We hope this study could shed some light on the future research of large-scale reinforcement learning.

fields

cs.MA 1 cs.SE 1

years

2026 1 2019 1

verdicts

UNVERDICTED 2

representative citing papers

On Multi-Agent Learning in Team Sports Games

cs.MA · 2019-06-25 · unverdicted · novelty 3.0

Describes a hierarchical RL method for multi-agent learning in team sports games aiming for human-like agents, reporting preliminary results that show promise.

citing papers explorer

Showing 2 of 2 citing papers.