An Introduction of mini-AlphaStar

• URL: http://arxiv.org/abs/2104.06890v1
• Date: Wed, 14 Apr 2021 14:31:51 GMT
• Title: An Introduction of mini-AlphaStar
• Authors: Ruo-Ze Liu, Wenhai Wang, Yanjie Shen, Zhiqi Li, Yang Yu, Tong Lu
• Abstract summary: An SC2 agent called AlphaStar is proposed which shows excellent performance, obtaining a high win-rates of 99.8% against Grandmaster level human players. We implemented a mini-scaled version of it called mini-AlphaStar based on their paper and the pseudocode they provided. The objective of mini-AlphaStar is to provide a reproduction of the original AlphaStar and facilitate the future research of RL on large-scale problems.
• Score: 22.820438931820764
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: StarCraft II (SC2) is a real-time strategy game, in which players produce and control multiple units to win. Due to its difficulties, such as huge state space, various action space, a long time horizon, and imperfect information, SC2 has been a research highlight in reinforcement learning research. Recently, an SC2 agent called AlphaStar is proposed which shows excellent performance, obtaining a high win-rates of 99.8% against Grandmaster level human players. We implemented a mini-scaled version of it called mini-AlphaStar based on their paper and the pseudocode they provided. The usage and analysis of it are shown in this technical report. The difference between AlphaStar and mini-AlphaStar is that we substituted the hyper-parameters in the former version with much smaller ones for mini-scale training. The codes of mini-AlphaStar are all open-sourced. The objective of mini-AlphaStar is to provide a reproduction of the original AlphaStar and facilitate the future research of RL on large-scale problems.

Related papers

• Rewrite the Stars [70.48224347277014]
  Recent studies have drawn attention to the untapped potential of the "star operation" in network design. Our study attempts to reveal the star operation's ability to map inputs into high-dimensional, non-linear feature spaces. We introduce StarNet, a simple yet powerful prototype, demonstrating impressive performance and low latency.
  arXiv  Detail & Related papers  (2024-03-29T04:10:07Z)
• AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning [38.75717733273262]
  StarCraft II is one of the most challenging simulated reinforcement learning environments. Blizzard has released a massive dataset of millions of StarCraft II games played by human players. We define a dataset (a subset of Blizzard's release), tools standardizing an API for machine learning methods, and an evaluation protocol.
  arXiv  Detail & Related papers  (2023-08-07T12:21:37Z)
• Targeted Search Control in AlphaZero for Effective Policy Improvement [93.30151539224144]
  We introduce Go-Exploit, a novel search control strategy for AlphaZero. Go-Exploit samples the start state of its self-play trajectories from an archive of states of interest. Go-Exploit learns with a greater sample efficiency than standard AlphaZero.
  arXiv  Detail & Related papers  (2023-02-23T22:50:24Z)
• Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning [95.78031053296513]
  No-press Diplomacy is a complex strategy game involving both cooperation and competition. We introduce a planning algorithm we call DiL-piKL that regularizes a reward-maximizing policy toward a human imitation-learned policy. We show that DiL-piKL can be extended into a self-play reinforcement learning algorithm we call RL-DiL-piKL.
  arXiv  Detail & Related papers  (2022-10-11T14:47:35Z)
• On Efficient Reinforcement Learning for Full-length Game of StarCraft II [21.768578136029987]
  We investigate a hierarchical RL approach involving extracted macro-actions and a hierarchical architecture of neural networks. On a 64x64 map and using restrictive units, we achieve a win rate of 99% against the level-1 built-in AI. We improve our architecture to train the agent against the cheating level AIs and achieve the win rate against the level-8, level-9, and level-10 AIs as 96%, 97%, and 94%, respectively.
  arXiv  Detail & Related papers  (2022-09-23T12:24:21Z)
• AlphaZero-Inspired General Board Game Learning and Playing [0.0]
  Recently, the seminal algorithms AlphaGo and AlphaZero have started a new era in game learning and deep reinforcement learning. In this paper, we pick an important element of AlphaZero - the Monte Carlo Tree Search (MCTS) planning stage - and combine it with reinforcement learning (RL) agents. We apply this new architecture to several complex games (Othello, ConnectFour, Rubik's Cube) and show the advantages achieved with this AlphaZero-inspired MCTS wrapper.
  arXiv  Detail & Related papers  (2022-04-28T07:04:14Z)
• SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II [15.612456049715123]
  AlphaStar, the AI that reaches GrandMaster level in StarCraft II, is a remarkable milestone demonstrating what deep reinforcement learning can achieve. We propose a deep reinforcement learning agent, StarCraft Commander ( SCC) SCC demonstrates top human performance defeating GrandMaster players in test matches and top professional players in a live event.
  arXiv  Detail & Related papers  (2020-12-24T08:43:44Z)
• DeepCrawl: Deep Reinforcement Learning for Turn-based Strategy Games [137.86426963572214]
  We introduce DeepCrawl, a fully-playable Roguelike prototype for iOS and Android in which all agents are controlled by policy networks trained using Deep Reinforcement Learning (DRL) Our aim is to understand whether recent advances in DRL can be used to develop convincing behavioral models for non-player characters in videogames.
  arXiv  Detail & Related papers  (2020-12-03T13:53:29Z)
• TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game [25.248034258354533]
  Recently, Google's DeepMind announced AlphaStar, a grandmaster level AI in StarCraft II that can play with humans using comparable action space and operations. In this paper, we introduce a new AI agent, named TStarBot-X, that is trained under orders of less computations and can play competitively with expert human players.
  arXiv  Detail & Related papers  (2020-11-27T13:31:49Z)
• Suphx: Mastering Mahjong with Deep Reinforcement Learning [114.68233321904623]
  We design an AI for Mahjong, named Suphx, based on deep reinforcement learning with some newly introduced techniques. Suphx has demonstrated stronger performance than most top human players in terms of stable rank. This is the first time that a computer program outperforms most top human players in Mahjong.
  arXiv  Detail & Related papers  (2020-03-30T16:18:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.