facebookresearch / Pearl
A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
☆2,784Updated this week
Alternatives and similar repositories for Pearl:
Users that are interested in Pearl are comparing it to the libraries listed below
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,742Updated 2 months ago
- A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.☆2,597Updated this week
- Really Fast End-to-End Jax RL Implementations☆833Updated 6 months ago
- LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.☆520Updated 4 months ago
- Schedule-Free Optimization in PyTorch☆2,110Updated 2 weeks ago
- High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, T…☆6,519Updated last week
- ☆2,879Updated 6 months ago
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,367Updated 11 months ago
- Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors a…☆1,301Updated this week
- Robust recipes to align language models with human and AI preferences☆5,046Updated 3 months ago
- ☆4,068Updated 9 months ago
- Monte Carlo tree search in JAX☆2,436Updated 3 months ago
- Fine-tune LLM agents with online reinforcement learning☆1,077Updated 11 months ago
- PyTorch native post-training library☆4,976Updated this week
- Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)☆2,911Updated 10 months ago
- Mastering Diverse Domains through World Models☆1,536Updated 2 weeks ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆5,872Updated 3 months ago
- Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.☆1,537Updated 3 weeks ago
- An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly…☆8,527Updated last week
- Simplifying reinforcement learning for complex game environments☆1,729Updated this week
- A PyTorch native library for large model training☆3,433Updated this week
- Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-…☆3,309Updated last month
- Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools.☆689Updated this week
- A simple, performant and scalable Jax LLM!☆1,647Updated this week
- Train transformer language models with reinforcement learning.☆12,395Updated this week
- High throughput synchronous and asynchronous reinforcement learning☆879Updated 2 months ago
- NanoGPT (124M) in 3 minutes☆2,367Updated this week
- TensorDict is a pytorch dedicated tensor container.☆891Updated this week
- What would you do with 1000 H100s...☆1,013Updated last year
- ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)☆3,267Updated 3 months ago