Search Packages

synalinks

From idea to production in just few lines: Graph-Based Programmable Neuro-Symbolic LM Framework - a production-first LM framework built with decade old Deep Learning best practices

nemo-gym

NeMo Gym is a library for building reinforcement learning environments

pyrddlgym-rl

Wrappers for reinforcement learning algorithms (i.e. stable baselines 3, RLlib) to work with pyRDDLGym.

easyagents

reinforcement learning for practitioners.

rlforge

RL Forge is an open source reinforcement learning library that aims to provide the users with useful functions for the development of Reinforcement Learning Agents. The library also includes multiple popular reinforcement learning agents and environments, in addition, it is designed to be compatible with the gymnasium library (previous OpenAI Gym).

infotheory-rs

Python bindings for the infotheory Rust library

lazaro

Reinforcement learning framework for implementing custom models on custom environments using state of the art RL algorithms

timeseries-agent

A Policy Gradient RL agent for time series prediction using PyTorch Lightning.

behavioralflow

Reinforcement learning library inspired by Behavioral Psychology, focused on simplicity. It uses Python dictionaries instead of complex tables, making implementation intuitive. Agents learn through reinforcement and punishment, considering context and consequences. They can also combine actions to create new behaviors.

reinforceui-studio

A GUI to simplify the configuration and monitoring of RL training processes.

evolverl

A package for evolving LLM agents through adversarial training

lrl

lrl: Learn Reinforcement Learning

mseep-synalinks

From idea to production in just few lines: Graph-Based Programmable Neuro-Symbolic LM Framework - a production-first LM framework built with decade old Deep Learning best practices

talia

An open-source UCI-compatible chess engine for 2 and 4 player chess.

tabular-rl

A simple Reinforcement Learning framework to decouple agents from environments in discrete-state settings with implementations of double Q-learning and policy iteration through dynamic programming.