Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
41 commits
Select commit Hold shift + click to select a range
d389b6e
werewolf game in progress
Keyu-He Sep 21, 2025
8b8850d
werewolf game in progress
Keyu-He Sep 21, 2025
2cc3990
updated prompt
Keyu-He Oct 31, 2025
22ae860
Fix custom/local model support bugs
Keyu-He Nov 13, 2025
3a9f689
current progress
Keyu-He Nov 13, 2025
df62578
fix mypy errors
Keyu-He Nov 13, 2025
f482b60
To run the local models
Keyu-He Nov 13, 2025
b453633
Design Social Game class, werewolf demo working in progress
Keyu-He Nov 14, 2025
7de839b
Merge branch 'main' into feature/social-game-support
Keyu-He Nov 20, 2025
ff49e41
update on the SocialGame class / SocialDeductionGame class
Keyu-He Nov 26, 2025
71711b6
fix mypy errors
Keyu-He Nov 26, 2025
39bb4e3
debugging on the prompts
Keyu-He Nov 30, 2025
eff40bf
refactor SocialDeductionGame for real-time history and fix some visib…
Keyu-He Dec 3, 2025
ca835c3
werewolf game debug
Keyu-He Dec 4, 2025
c0f7866
Refactor social_game.py and update werewolves example
Keyu-He Dec 7, 2025
089b30c
Add Social Game Engine documentation
Keyu-He Dec 7, 2025
4ce9d6c
Delete examples/experimental/negotiation_arena/NegotiationArena_1_Buy…
Keyu-He Dec 7, 2025
39f46cd
Restore sotopia/cli/install/redis-data/dump.rdb to match origin/main
Keyu-He Dec 7, 2025
aacd07a
Revert unnessarily changes in the uniform_sample and server.py
Keyu-He Dec 7, 2025
f676238
Minor update on werewolf prompt, Compatibility on uniform sampler and…
Keyu-He Dec 7, 2025
67dc7db
update uniform_sampler and server.py to the correct versions
Keyu-He Dec 7, 2025
d48f71d
move visibility prompt inside werewolf game's config
Keyu-He Dec 7, 2025
37039de
add more example games, add elo score calculation
Keyu-He Dec 9, 2025
f0aa8a9
Refactor ELO tournament system with parallel execution and enhanced l…
Keyu-He Dec 9, 2025
9a6b115
Move logging configuration to main entry points
Keyu-He Dec 9, 2025
daca3f4
Update run_elo_tournament.py
Keyu-He Dec 9, 2025
2160f7b
Improve ELO leaderboard reporting and roster generation
Keyu-He Dec 16, 2025
e2c0129
feat: make structured_output configurable in agenerate_action
Keyu-He Feb 13, 2026
7523bd2
Add 21 multiplayer games with zero-sum scoring and ELO tournament runner
Keyu-He Mar 13, 2026
47cd288
Remove threshold mechanic: pure score comparison for zero-sum games
Keyu-He Mar 13, 2026
27ebd86
Fix ELO: all-pairs updates for multi-player, cross-team-only for team…
Keyu-He Mar 13, 2026
e9a9413
Battle of the Sexes: add Discuss phase before each Choose round
Keyu-He Mar 13, 2026
18259bf
Split ELO leaderboard into competitive and cooperative sections
Keyu-He Mar 13, 2026
118b10b
Win rate color gradient: red=0% green=100%
Keyu-He Mar 13, 2026
5546b66
Add reflection injection support to game engine and all 21 games
Keyu-He Apr 1, 2026
499be54
ELO: add model name normalization, cooperative game split, team game …
Keyu-He Apr 1, 2026
fd05270
Tournament runner: parallel across games, roster_dir dedup, remove pa…
Keyu-He Apr 1, 2026
ba7e609
Roster gen: deterministic seeding, self-play support, experiment rost…
Keyu-He Apr 1, 2026
137a8b9
Add play-reflect-transfer pipeline and GPT-5 werewolf reflection
Keyu-He Apr 1, 2026
4ffa085
Add reflection results notebook and ELO leaderboard
Keyu-He Apr 1, 2026
a5d7eca
Clean up game configs/descriptions: remove dead thresholds, fix misma…
Keyu-He Apr 17, 2026
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -167,3 +167,9 @@ redis-data/*
sotopia/cli/install/redis-data/*
redis-stack-server-*/
examples/experimental/negotiation_arena/redis-data/*
*.rdb
*.dot
logs/*
experiments/rosters/*
experiments/results/*
CLAUDE.md
Loading