🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

Online Deep Learning: Learning Deep Neural Networks on the Fly / Non-linear Contextual Bandit Algorithm (ONN_THS)

👤 Multi-Armed Bandit Algorithms Library (MAB) 👮

This repository contains the source code for “Thompson sampling efficient multiobjective optimization” (TSEMO).

Windows desktop app with an adaptive AI orchestrator for Flowseal strategies, automatic tuning and network-aware profile selection

Library for multi-armed bandit selection strategies, including efficient deterministic implementations of Thompson sampling and epsilon-greedy.

Thompson Sampling Tutorial

Python library for Multi-Armed Bandits

All codes, both created and optimized for best results from the SuperDataScience Course

In This repository I made some simple to complex methods in machine learning. Here I try to build template style code.

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

Bandit algorithms

pyrff: Python implementation of random fourier feature approximations for gaussian processes

ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.

Study of the paper 'Neural Thompson Sampling' published in October 2020

Offline evaluation of multi-armed bandit algorithms

The official code release for "Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning", ICLR 2025

A Julia Package for providing Multi Armed Bandit Experiments

Bayesian Optimization for Categorical and Continuous Inputs

A curated list on papers about combinatorial multi-armed bandit problems.