https://github.com/baskuit/r-nad

Experimentation with Regularized Nash Dynamics on a GPU accelerated game

deepnash multiagent-reinforcement-learning pytorch reinforcement-learning reinforcement-learning-algorithms rnad

Last synced: 19 Aug 2025

https://github.com/baskuit/pinyon

Pinyon is a collection of algorithms and utilities for research in search/planning in simultaneous move games.

alphazero cpp games mcts pokemon search

Last synced: 14 Oct 2025

https://github.com/baskuit/dolly

Modification of monobeast to apply R-NaD to Pokemon-Showdown

deep-learning monobea

Last synced: 25 Mar 2025

https://github.com/baskuit/oak

Last synced: 25 Mar 2025

https://github.com/baskuit/lrslib

Minimal solver of bimatrix games extracted from lrslib (See below).

bimatrix-game nash-equilibrium

Last synced: 25 Mar 2025

https://github.com/baskuit/cuda-pinyon-demo

Offline training of a Libtorch NN using monte-carlo generated search data. Uses very fast Zig simulator @pkmn/engine and templated C++ search library Pinyon for the actors, with minimal CUDA backend.

Last synced: 07 Sep 2025

https://github.com/baskuit/rkea.net

Last synced: 07 Feb 2026

https://github.com/baskuit/kenshinrpc

Last synced: 01 Aug 2025

https://github.com/baskuit/alpha-zero-rby

Last synced: 01 Aug 2025

https://github.com/baskuit/taurus

Last synced: 25 Mar 2025

https://github.com/baskuit/pkmn-pinyon-test

Testing the use of Pinyon search utilities with pkmn/engine

Last synced: 25 Mar 2025