Train a Deep Q-Network on remote GPUs, but execute its policy in JS
Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear
Self-contained RL trading bot with DQN, PER, and market simulation
<h1 align="center"> <br> <a href="https://github.com/keppel/weblearn-dqn"><img src="https://cloud.githubusercontent.com/assets/1269291/21950583/6d22659c-d9b1-11e6-8fb4-2d61b196b688.gif" alt="WebLearn DQN" width="400"></a> <br> WebLearn DQN <br>
Self-Optimizing Neural Architecture (SONA) for Cognition — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual learni
The Reinforcement Learning with Deep Q-Networks (DQN) is a Python class that implements the DQN algorithm for reinforcement learning tasks. It allows agents to learn optimal policies through interaction with an environment using Q-learning and deep neural
A collection of various reinforcement learning solver. The library is an object-oriented approach (baked with Typescript) and tries to deliver simplified interfaces that make using the algorithms pretty simple.
Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear
Fractal-RL is a lightweight and easy-to-use reinforcement learning library for TypeScript and JavaScript. It provides implementations of popular deep reinforcement learning algorithms, including Deep Q-Network (DQN) and Proximal Policy Optimization (PPO).
Reinforcement learning in javascript
Neural module - SONA learning integration, neural modes
**@brain/rl** is a Reinforcement Learning library that implements several common RL algorithms, all with web demos. In particular, the library currently includes:
This is a node.js module that contains helper functions used in AllanBot.
<!-- <img src="./assets/rlts.png" style="zoom:20%;" /> -->
Self-learning dynamic pricing with RL optimization and swarm strategy exploration
<!-- <img src="./assets/rlts.png" style="zoom:20%;" /> -->
Reinforcement Learning library
A library using TensorFlow.js for Deep Reinforcement Learning
A library using TensorFlow.js for Deep Reinforcement Learning
This is a simple framework for implementing and testing reinforcement learning environments and algorithms
TensorFlow.js backend for IgnitionAI - browser-based reinforcement learning framework
ONNX inference backend for IgnitionAI — cross-platform, production-ready RL inference
Contains Classes specific for usage in a node environment.
Contains Classes specific for usage in a web environment usage.
Deep reinforcement learning algorithms for rlevo (internal crate — use `rlevo` for the full API)
A deep reinforcement learning library based on Rust and Candle, providing complete implementations of Q-Learning and DQN algorithms, supporting custom environments, various policy choices, and flexible training configurations. Future support will include more reinforcement learning algorithms, such as DDPG, PPO, A2C, etc.
RL-based article extraction from HTML using Deep Q-Networks and heuristic fallback
RL-based article extraction from HTML using Deep Q-Networks and heuristic fallback
Reinforcement learning algorithm implementations (DQN, PPO, SAC) using Burn
Provides a generator for a deep q-learning network. Allows for random training intervals, and will be updated to a more stable version later.
Deep Reinforcement Learning Framework
Reinforcement learning algorithms for the Burn ML framework
Scivex — Reinforcement learning: environments, DQN, PPO, A2C
Pure-Rust Double/Dueling Deep Q* reinforcement-learning agent — no external ML framework dependency.
Safe Rust. No Deps. RL for the CPU.
Reinforcement learning for Rust. Backend-agnostic over modern Rust ML frameworks.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.