facebookresearch / Pearl
A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
☆2,810Updated last week
Alternatives and similar repositories for Pearl:
Users that are interested in Pearl are comparing it to the libraries listed below
- A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.☆2,685Updated this week
- Fine-tune LLM agents with online reinforcement learning☆1,108Updated last year
- High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, T…☆6,880Updated 2 weeks ago
- Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools.☆738Updated this week
- Really Fast End-to-End Jax RL Implementations☆859Updated 7 months ago
- Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.☆2,547Updated 11 months ago
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,759Updated this week
- Thunder gives you PyTorch models superpowers for training and inference. Unlock out-of-the-box optimizations for performance, memory and …☆1,328Updated this week
- Massively parallel rigidbody physics simulation on accelerator hardware.☆2,634Updated this week
- Mastering Diverse Domains through World Models☆1,769Updated 2 weeks ago
- An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly…☆8,968Updated last week
- TensorDict is a pytorch dedicated tensor container.☆911Updated this week
- LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.☆547Updated 6 months ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆5,930Updated 2 weeks ago
- A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents include…☆2,381Updated 3 weeks ago
- PyTorch code and models for V-JEPA self-supervised learning from video.☆2,940Updated last month
- C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.☆1,147Updated 8 months ago
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,378Updated last year
- A library of reinforcement learning components and agents☆3,655Updated last week
- Tools for merging pretrained large language models.☆5,571Updated this week
- Monte Carlo tree search in JAX☆2,467Updated 2 weeks ago
- A PyTorch native library for large-scale model training☆3,627Updated this week
- ☆1,309Updated last week
- An offline deep reinforcement learning library☆1,441Updated 2 weeks ago
- High throughput synchronous and asynchronous reinforcement learning☆888Updated 3 months ago
- Training LLMs with QLoRA + FSDP☆1,472Updated 5 months ago
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,360Updated last week
- An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities☆2,886Updated this week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,659Updated this week
- Robust recipes to align language models with human and AI preferences☆5,138Updated 5 months ago