Skip to content

Milestone 2: Alphazero implementation - #588

Draft
Eyepatch0 wants to merge 4 commits into
gpsaggese:masterfrom
Eyepatch0:UmdTask507_AlphaZero
Draft

Eyepatch0 wants to merge 4 commits into
gpsaggese:masterfrom
Eyepatch0:UmdTask507_AlphaZero

Conversation

@Eyepatch0

Copy link
Copy Markdown
Contributor

Adds an AlphaZero game-representation API under research/Implement_AlphaZero/, reusing the existing game rules. The utilities provide player-relative board encodings, fixed-size legal-action masks, and exact terminal values that distinguish unfinished games from draws.

Includes a paired Tic-Tac-Toe API notebook, usage documentation, and a Python 3.12 slim CPU Docker image using the shared project scripts. The notebook walks through board encodings, legal moves, a complete game, and terminal outcomes.

Validation:

  • Docker image built successfully.
  • Notebook executed successfully in fresh local and Docker kernels.
  • Notebook pairing, Python formatting, shell syntax, and symlink checks passed.

Related to #507.

…, and CPU Docker setup

Pre-commit checks:
All checks passed ✅
@Eyepatch0 Eyepatch0 changed the title UmdTask507: Add AlphaZero game representation tutorial and CPU Docker setup Milestone 2: Alphazero implementation Sep 18, 2026
@Eyepatch0
Eyepatch0 marked this pull request as draft September 18, 2026 20:01
…and documentation

Pre-commit checks:
All checks passed ✅
Pre-commit checks:
All checks passed ✅
Pre-commit checks:
All checks passed ✅
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant