lcipolina/game_reasoning_arena

Added Name cleaner for OpenRouter models

Deleted as it seems to be empty

Not needed

Deletd because code is not working

Deletd because code is not working

Updated matching pennies

Updated with Matching Pennies and more runs

Updated with Hex

Added debugging for Hex

Upload app.py

Updated with Hex

Updated with Hex

Updated with Hex

Enhanced model name cleaner

Improved modularization and model names

Fixed long names on Leaderboard

Fixed long names in leaderboards

Added additional models

Prevents human vs human tournament

Fixed horrible legend and wording

Fixed the # games

Updated results with more LLM models

Fixed typo

Auto start when the Player 0 is random or LLM

Added string regarding poor reasoning outputs

Fixed human player

Fixes and refactoring

Fixed human and cleaning code

Fixed drop down options for human

Fixed human agent

Fixed human player

Added human agent

Added human agent for Gradio interface

Added human player

Inverted plots axes for better display

Fixed players labelling

Removed time stamp and deleted duplicates matrix_pd in leaderboard

Fixed duplication on prisoners dilemma

Updated results files

Fixed parsing of the config files

Fixed parsing of the config files

Fixed parsing of the configs

Added parser for multi games

Added logging of rewards

Added debugging options

Fixed bug in the human agent

Include back the aggregated performance

Updated the drop down of the leaderboard

Deduplication of entries in the game drop down

Updated to use the current time as the random seed