Ppo Python Packages

tianshou

An elegant PyTorch deep reinforcement learning library.

auto-mdp-solver

Formalize a verbal dynamic-decision problem into an MDP, then train and interpret a deployable RL policy — as Claude Code skills with executable gates between stages

miniverl

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.

actorch

Deep reinforcement learning framework for fast prototyping based on PyTorch

rustforge-rl

A pure Rust Reinforcement Learning framework featuring a custom tensor engine, autograd system, and modular RL algorithms.

autonomous-learning-library

A PyTorch library for building deep reinforcement learning agents.

elegantrl

Massively Parallel Deep Reinforcement Learning. 🔥

evorl-jax

EvoRL is a fully GPU-accelerated framework for Evolutionary Reinforcement Learning, implemented with JAX. It supports Reinforcement Learning (RL), Evolutionary Computation (EC), Evolution-guided Reinforcement Learning (ERL), AutoRL, and seamless integration with GPU-optimized simulation environments.

oat-llm

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

redco

NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference

neodroidagent

Examples of agents for neodroid environments 💡

atomic-rl

Reinforcement learning utilities for Deep RL and the Alberta Plan: readable implementations of DQN, Rainbow, PPO, and MCTS.

reinfors

High-throughput reinforcement-learning search and sampling in Rust, with caller-owned Python networks and training

rlox

Rust-accelerated reinforcement learning — 22 algorithms, 2-10x faster than SB3. The Polars of RL.

rllte-core

Long-Term Evolution Project of Reinforcement Learning

xuance

XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library

rllib

A simple and neat implementation of reinforcement learning algorithms.

probe-the-harness

Setup checks for stale-data RL comparisons in language models

deepcomp

Dynamic multi-cell selection for cooperative multipoint (CoMP) using (multi-agent) deep reinforcement learning

rainy

:umbrella: Deep RL agents with PyTorch:umbrella:

decisionrl

Reinforcement learning for operational decisions — pricing, inventory, energy, queues, supply chains. 32 algorithms, typed, tested.

machin

Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...

toyrl

Reinforce learning is awesome!

telekinesis-rlbotics

Lightweight, GPU-accelerated reinforcement learning for Isaac Lab, mjlab, and Gymnasium.