Yahoo! news article recommendation system by linUCB
-
Updated
Feb 1, 2018 - Python
#
contextual-bandit
Here are 24 public repositories matching this topic...
The AI study agent that learns how you learn — RL picks the action, FSRS picks the timing, the LLM only writes the quizzes. Chrome extension · Anki export · MCP server · runs on Ollama
chrome-extension education reinforcement-learning mcp q-learning spaced-repetition anki pomdp ai-agents contextual-bandit huggingface streamlit agent-framework study-assistant study-tool ai-agent claude-api fsrs ai-tutor mcp-server
-
Updated
Aug 2, 2026 - JavaScript
A gymnasium-compatible framework to create reinforcement learning (RL) environment for solving the optimal power flow (OPF) problem. Contains five OPF benchmark environments for comparable research.
benchmark environment reinforcement-learning supervised-learning rl optimal-power-flow energy-system gymnasium opf pandapower contextual-bandit reward-design reward-shaping power-system environment-design action-shaping
-
Updated
Mar 22, 2025 - Python
Bandit algorithms
-
Updated
Oct 12, 2017 - Python
Implementation of the Adaptive Contextual Combinatorial Upper Confidence Bound (ACC-UCB) algorithm for the contextual combinatorial volatile multi-armed bandit setting.
-
Updated
Feb 24, 2020 - Python
Context Runtime — a database query planner for LLM context. Decides what a model sees before it answers; plans it, runs it through reused substrate, and learns from the outcome.
python golang retrieval mcp self-hosted semantic-search observability cost-optimization contextual-bandit explainable-ai multimodal rag query-planner llm llmops context-management agentic-ai ai-infrastructure context-engineering context-runtime
-
Updated
Aug 5, 2026 - Python
Deterministic decision-intelligence MCP server for AI agents — 17 tools (bandits/LinUCB, HiGHS LP/MIP, PageRank, Monte Carlo, CMA-ES, conformal). Sub-25ms. Zero LLM cost. 11 free, no key. Listed on the MCP Registry & Glama.
api machine-learning typescript algorithms optimization mcp monte-carlo linear-programming pagerank bandits fastify ai-agents contextual-bandit decision-intelligence anthropic llm-tools agent-tools model-context-protocol claude-mcp deterministic-tools
-
Updated
Aug 11, 2026 - TypeScript
Code for our AJCAI 2020 paper: "Online Semi-Supervised Learning in Contextual Bandits with Episodic Reward".
reinforcement-learning paper semi-supervised-learning bandits bandit contextual-bandits contextual-bandit self-supervised-learning nonstationary-environments
-
Updated
Sep 21, 2020 - MATLAB
EchoRun AI跑酷 - 源码仓库 (私有, 含AI影子对战+微信小游戏分支)
android webgl csharp endless-runner procedural-generation unity game-development contextual-bandit behavior-cloning tuanjie-engine
-
Updated
Aug 12, 2026 - C#
An illustrative project including some multi-armed bandit algorithms and contextual bandit algorithms
-
Updated
Feb 3, 2021 - Python
Contextual bandit implementation using Keras
-
Updated
Apr 30, 2018 - Python
Adaptive AI companion that builds a model of each user from implicit interaction signals — keystroke dynamics, linguistic complexity, temporal patterns — and continuously adapts its responses. Custom TCN + transformer + contextual bandit, built from scratch in PyTorch.
python machine-learning deep-learning websocket poetry pytorch personalization transformer thompson-sampling language-model user-modeling from-scratch huawei contextual-bandit privacy-by-design adaptive-systems human-machine-interaction fastapi edge-ai temporal-convolutional-network
-
Updated
Apr 29, 2026 - Python
Reinforcement learning (PPO/A2C/DQN) that dynamically tunes Anti-Money-Laundering risk-scoring weights per case — Gymnasium env, FastAPI backend, and a React training dashboard.
react machine-learning reinforcement-learning gymnasium aml regtech ppo contextual-bandit anti-money-laundering fastapi risk-scoring stable-baselines3
-
Updated
Jul 16, 2026 - Python
Bayesian multi-armed bandits for continuous prompt experimentation: Thompson sampling routes traffic to the best prompt variant and a stopping rule promotes a winner without a fixed-N A/B test. Zero dependencies, TypeScript-first.
nodejs typescript mcp edge openai thompson-sampling experimentation ab-testing bayesian zero-dependency multi-armed-bandit bandit contextual-bandit best-arm-identification sequential-testing llm prompt-engineering anthropic beta-bernoulli prompt-experimentation
-
Updated
Jun 22, 2026 - TypeScript
An experience engine for AI agents. Retrieval as a contextual bandit, not a search.
reinforcement-learning ai-agents contextual-bandit linucb continual-learning experience-replay llm agent-memory
-
Updated
Jul 13, 2026 - Python
Contextual bandit (LinUCB) that re-tunes PID gains for a line-following robot as its chassis changes
reinforcement-learning robotics pid-control adaptive-control contextual-bandit linucb robotics-education
-
Updated
Apr 21, 2026 - Python
-
Updated
Nov 16, 2017 - Python
Contextual Multi-Armed Bandit that automates credit limit decisions for 10,000 users using Thompson Sampling — beats static limits by 30%+ with an interactive Streamlit dashboard.
python data-science machine-learning reinforcement-learning fintech thompson-sampling multi-armed-bandit credit-risk contextual-bandit streamlit
-
Updated
May 23, 2026 - HTML
A Reinforcement Learning approach to a contextual bandit problem.
reinforcement-learning reinforcement-learning-algorithms bandit-learning markov-decision-processes contextual-bandit
-
Updated
Dec 2, 2017 - Jupyter Notebook
Improve this page
Add a description, image, and links to the contextual-bandit topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the contextual-bandit topic, visit your repo's landing page and select "manage topics."