Pinned Loading

1. rl-cart-pole rl-cart-pole Public

   A Deep Q-Network (DQN) implementation for solving the CartPole-v1 environment using PyTorch and Gymnasium.

   Python

2. rl-drive-taxi rl-drive-taxi Public

   A reinforcement learning implementation using Q-learning to solve the classic Taxi-v3 environment from OpenAI Gymnasium. The agent learns to navigate a 5x5 grid world, pick up passengers, and drop …

   Python

3. rl-frozen-lake rl-frozen-lake Public

   A comprehensive implementation of Q-Learning reinforcement learning algorithm applied to the FrozenLake environment from Gymnasium. This project demonstrates how an agent learns to navigate through…

   Python

4. subconv subconv Public

   A tool that translates SRT subtitle files to any language using OpenAI's API (or usable models in openai api). It processes subtitles asynchronously in batches for efficient translation while prese…

   Python

5. quieto quieto Public

   High-performance async debounce library for Python 3.13+ with message coalescing, designed for LLM-powered applications.

   Python

6. agent-skills agent-skills Public

   A collection of skills for AI coding agents. Skills are packaged instructions and reference materials that extend what an agent can do.