Search Results for "self learning"

...Configuration is managed via protobuf files to define tasks such as self-play, benchmark agent comparisons, and RL training. The project is now archived and read-only, reflecting that it is no longer actively developed but remains publicly available for research use.

glsmac is a compact C99 library designed to simplify OpenGL development on macOS by creating a minimal, no-dependency window and OpenGL context setup. It uses only macOS's native APIs (Cocoa and Core OpenGL) without relying on third-party frameworks like GLFW or SDL. This makes it ideal for developers who want tight control over their OpenGL projects, need a lightweight setup for demos or testing, or are writing small graphical utilities without overhead. The code is short, self-contained,...

ELF (Extensive, Lightweight, and Flexible) is a high-performance platform for reinforcement learning research that unifies simulation, data collection, and distributed training. A C++ core provides fast environments and concurrent actors, while Python bindings expose simple APIs for agents, replay, and optimization loops. It supports both single-agent and multi-agent settings, with batched stepping and shared-memory queues that keep GPUs saturated during training.

NeuroDraughts is a Draughts/Checkers game that teaches itself how to play through self play. It combines an Artificial Neural Network, trained by Temporal Difference Learning using some Genetic Algorithm style behaviour.

There are lots of bots out for Half-Life. Many closed source or Windows only. All of them are based on Botmans Code ( http://www.planethalflife.com/botman ). The goal of this project is to make a self-learning, waypointless, opensource, Linux+Win. Bot