Record

event

Multi Agent Reinforcement Learning: AlphaStar Introduction

Tue, Nov 3, 1:30 AM UTC

by @curator.boulderevents.directorydid:plc:7ucd6qjmlenanyswjx5hcvko · indexed 4d ago

Merged into a curated record: Multi Agent Reinforcement Learning: AlphaStar Introduction

at://did:plc:7ucd6qjmlenanyswjx5hcvko/community.lexicon.calendar.event/3my6zk74t7kfx

Index now reads it again from its author's repo. Take down hides it here only.

Upstream

no upstream named

From

no credit named

Raw JSON

event

{
  "$type": "community.lexicon.calendar.event",
  "additionalData": {
    "category": "education",
    "externalSource": {
      "externalId": "event_317041285@meetup.com",
      "method": "meetup",
      "platform": "meetup",
      "profile": 1,
      "rsvpMode": "external_only",
      "syncedAt": "2026-11-03T01:32:15.654Z",
      "url": "https://meetup.com/boulderdatascience/events/317041285"
    }
  },
  "createdAt": "2026-10-19T02:00:20.735Z",
  "createdWith": "https://boulderevents.directory",
  "description": "Boulder Data Science, Machine Learning & AI\nThis meeting will continue with section Chapter 9.9.3 of [Multi-Agent Reinforcement Learning: Foundations and Modern Approaches](https://www.marl-book.com/) which discusses the DeepMind agent AlphaStar and its league training approach to developing robust strategies. We have a general overview of the AlphaStar project and look at the initial test results in some detail. We will begin with the first [blog post](https://deepmind.google/blog/alphastar-mastering-the-real-time-strategy-game-starcraft-ii/) published by DeepMind on the topic and the associated live demonstration. Eventually we will also look at the associated [blog post and Nature paper](https://deepmind.google/blog/alphastar-grandmaster-level-in-starcraft-ii-using-multi-agent-reinforcement-learning/) that were published later that year.\n\nYou can find below links to notes and recordings of previous meetings.\nMeetup Links:\n[Recordings of Previous RL Meetings](https://youtube.com/playlist?list=PLYqXmZaxvwmy2CNaK-DLailou1VIU1UZn&si=n6uQm863MCcHuKT7)\n[Recordings of Previous MARL Meetings](https://youtube.com/playlist?list=PLYqXmZaxvwmzikjw-cNyZfI051ms05czB&si=A7-AeX0dcRW67PDB)\n[Short RL Tutorials](https://youtube.com/playlist?list=PLYqXmZaxvwmyLEXMpk-n4RFr59tpJjNXt&si=RHy_FAnOJnPa4p1N)\n[My exercise solutions and chapter notes for Sutton-Barto](https://github.com/jekyllstein/Reinforcement-Learning-Sutton-Barto-Exercise-Solutions)\n[My MARL repository](https://github.com/jekyllstein/MARL_course/tree/main)\n[Kickoff Slides which contain other links](https://docs.google.com/presentation/d/1QD3iw5BgIpPpl_K_ApAlDr1NRseR1WmXme1dKQGqTOg/edit?usp=sharing)\n[MARL Kickoff Slides](https://docs.google.com/presentation/d/1FHXGVWkzjKsnNxzVN-29dx5vdkffAx5Vji5nWrDvg1Y/edit?usp=sharing)\nMARL Links:\n[Multi-Agent Reinforcement Learning: Foundations and Modern Approaches](https://www.marl-book.com/)\n[MARL Summer Course Videos](https://youtube.com/playlist?list=PLkoCa1tf0XjCU6GkAfRCkChOOSH6-JC_2&si=lEljXo65s3fMUsRC)\n[MARL Slides](https://github.com/marl-book/slides)\nSutton and Barto Links:\n[Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto](http://incompleteideas.net/book/the-book.html)\n[Video lectures from a similar course](https://youtube.com/playlist?list=PLqYmG7hTraZDVH599EItlEWsUOsJbAodm)",
  "endsAt": "2026-11-02T20:00:00.000-07:00",
  "facets": [
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://www.marl-book.com/"
        }
      ],
      "index": {
        "byteEnd": 199,
        "byteStart": 173
      }
    },
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://deepmind.google/blog/alphastar-mastering-the-real-time-strategy-game-starcraft-ii/"
        }
      ],
      "index": {
        "byteEnd": 548,
        "byteStart": 458
      }
    },
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://deepmind.google/blog/alphastar-grandmaster-level-in-starcraft-ii-using-multi-agent-reinforcement-learning/"
        }
      ],
      "index": {
        "byteEnd": 814,
        "byteStart": 700
      }
    },
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://youtube.com/playlist?list=PLYqXmZaxvwmy2CNaK-DLailou1VIU1UZn&si=n6uQm863MCcHuKT7"
        }
      ],
      "index": {
        "byteEnd": 1064,
        "byteStart": 976
      }
    },
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://youtube.com/playlist?list=PLYqXmZaxvwmzikjw-cNyZfI051ms05czB&si=A7-AeX0dcRW67PDB"
        }
      ],
      "index": {
        "byteEnd": 1193,
        "byteStart": 1105
      }
    },
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://youtube.com/playlist?list=PLYqXmZaxvwmyLEXMpk-n4RFr59tpJjNXt&si=RHy_FAnOJnPa4p1N"
        }
      ],
      "index": {
        "byteEnd": 1304,
        "byteStart": 1216
      }
    },
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://github.com/jekyllstein/Reinforcement-Learning-Sutton-Barto-Exercise-Solutions"
        }
      ],
      "index": {
        "byteEnd": 1450,
        "byteStart": 1365
      }
    },
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://github.com/jekyllstein/MARL_course/tree/main"
        }
      ],
      "index": {
        "byteEnd": 1525,
        "byteStart": 1473
      }
    },
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://docs.google.com/presentation/d/1QD3iw5BgIpPpl_K_ApAlDr1NRseR1WmXme1dKQGqTOg/edit?usp=sharing"
        }
      ],
      "index": {
        "byteEnd": 1670,
        "byteStart": 1570
      }
    },
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://docs.google.com/presentation/d/1FHXGVWkzjKsnNxzVN-29dx5vdkffAx5Vji5nWrDvg1Y/edit?usp=sharing"
        }
      ],
      "index": {
        "byteEnd": 1794,
        "byteStart": 1694
      }
    },
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://www.marl-book.com/"
        }
      ],
      "index": {
        "byteEnd": 1906,
        "byteStart": 1880
      }
    },
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://youtube.com/playlist?list=PLkoCa1tf0XjCU6GkAfRCkChOOSH6-JC_2&si=lEljXo65s3fMUsRC"
        }
      ],
      "index": {
        "byteEnd": 2024,
        "byteStart": 1936
      }
    },
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://github.com/marl-book/slides"
        }
      ],
      "index": {
        "byteEnd": 2075,
        "byteStart": 2040
      }
    },
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "http://incompleteideas.net/book/the-book.html"
        }
      ],
      "index": {
        "byteEnd": 2229,
        "byteStart": 2184
      }
    },
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://youtube.com/playlist?list=PLqYmG7hTraZDVH599EItlEWsUOsJbAodm"
        }
      ],
      "index": {
        "byteEnd": 2338,
        "byteStart": 2270
      }
    }
  ],
  "media": [
    {
      "alt": "Reinforcement Learning: Topic TBA",
      "aspect_ratio": {
        "height": 676,
        "width": 676
      },
      "content": {
        "$type": "blob",
        "mimeType": "image/jpeg",
        "ref": {
          "$link": "bafkreiauee7jlfx3uzjdxaqiow4b2fffkfj3c7ab7gruys5d6oyks26j74"
        },
        "size": 41500
      },
      "role": "thumbnail"
    }
  ],
  "mode": "community.lexicon.calendar.event#inperson",
  "name": "Multi Agent Reinforcement Learning: AlphaStar Introduction",
  "preferences": {
    "showInDiscovery": true
  },
  "startsAt": "2026-11-02T18:30:00.000-07:00",
  "status": "community.lexicon.calendar.event#scheduled",
  "timezone": "America/Denver",
  "uris": [
    {
      "name": "RSVP on Meetup",
      "uri": "https://meetup.com/boulderdatascience/events/317041285"
    }
  ]
}

Its way through the pipeline

The whole pipeline

On source recordsOn curated records

eventMulti Agent Reinforcement Learning: AlphaStar Introduction merged · open cluster

Geocodenothing writtenPlace matchnothing writtenMigrationnothing writtenAdjudicatornothing writtenEvent matchnothing writtenTakedownsnothing writtenCuratorwroteFeatureswrote

Curatorwrotemerged it with 0 other copies
Featureswrotereceipt for the current curated record

What the rules say about it

0 about it

Nothing yet. No rule has published anything about this record.