Skip to content

Multi-Agent Tooling for LuxAI

active 2024-02-052024-06-02 (UTC)

Complete coverage26,394 / 26,394 hourly files (100%) · 2 absent upstream2023-08-152026-08-18 (UTC)
Events
663
Pushes
556
Pull requests
0
Issues
44
Stars
1
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 119 days from 2024-02-05 to 2024-06-02. Pushes: 556 total, peak 33 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 44 total, peak 10 in a day. Comments: 3 total, peak 2 in a day. Stars: 1 total, peak 1 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
GergelyMagyar45443303
Getlar14912300

Recent activity

Latest issues, pull requests and releases

  • Issue#75Getlar2024-06-02 21:47
    Try different training parameters
  • Issue#76Getlar2024-06-02 21:47
    Play tournament with Kaggle models
  • Issue#66Getlar2024-06-02 21:46
    Play the trained agent against one of the open source models from Kaggle.
  • Issue#72Getlar2024-06-02 21:46
    Find simplified model that keep factories alive
  • Issue#73Getlar2024-06-02 21:46
    Train baseline to 2.5M steps
  • Issue#74Getlar2024-06-02 21:46
    Play matches with the trained model
  • Issue#59Getlar2024-06-02 21:46
    Finish testing results on Wiki for Monolithic Architecture (v0.0.1)
  • Issue#64Getlar2024-06-02 21:46
    Train an agent locally and colab.
  • Issue#65Getlar2024-06-02 21:46
    Check GPU/CPU/RAM requirements for different num_environment sizes.
  • Issue#70GergelyMagyar2024-03-03 21:26
    Improve action masking
  • Issue#77GergelyMagyar2024-03-03 21:26
    Separate rewards for individual units or groups
  • Issue#77GergelyMagyar2024-02-27 16:06
    Separate rewards for individual units or groups
  • Issue#71GergelyMagyar2024-02-27 16:03
    Create simplied reward models
  • Issue comment#70GergelyMagyar2024-02-19 20:53
    Improve action masking
  • Issue comment#70GergelyMagyar2024-02-19 20:50
    Improve action masking
  • Issue#76Getlar2024-02-19 16:17
    Play tournament with Kaggle models
  • Issue#75Getlar2024-02-19 16:16
    Try different training parameters
  • Issue#74Getlar2024-02-19 16:16
    Play matches with the trained model
  • Issue#73Getlar2024-02-19 16:14
    Train baseline to 2M steps
  • Issue#72GergelyMagyar2024-02-19 15:54
    Find simplified model that keep factories alive
  • Issue#71GergelyMagyar2024-02-19 15:53
    Create simplied reward models
  • Issue#70GergelyMagyar2024-02-19 15:53
    Improve action masking
  • Issue#63GergelyMagyar2024-02-19 15:52
    Move Action-per-Agent archiecture over to v0.0.2
  • Issue#69GergelyMagyar2024-02-19 15:52
    Train per unit v.0.0.2 on colab
  • Issue#69GergelyMagyar2024-02-18 12:04
    Train per unit v.0.0.2 on colab

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1 stars here means stars gained during the window, not the repo's star count.