Open Source Python Reinforcement Learning Libraries - Page 3

TensorLayer is a novel TensorFlow-based deep learning and reinforcement learning library designed for researchers and engineers. It provides an extensive collection of customizable neural layers to build advanced AI models quickly, based on this, the community open-sourced mass tutorials and applications. TensorLayer is awarded the 2017 Best Open Source Software by the ACM Multimedia Society. This project can also be found at OpenI and Gitee. 3.0.0 has been pre-released, the current version supports TensorFlow, MindSpore and PaddlePaddle (partial) as the backends, allowing users to run the code on different hardware like Nvidia-GPU and Huawei-Ascend. In the future, it will support TensorFlow, MindSpore, PaddlePaddle, PyTorch and other backends. TensorLayer has a high-level layer/model abstraction which is effortless to learn. You can learn how deep learning can benefit your AI tasks in minutes through the massive examples.

Texar is a toolkit aiming to support a broad set of machine learning, especially natural language processing and text generation tasks. Texar provides a library of easy-to-use ML modules and functionalities for composing whatever models and algorithms. The tool is designed for both researchers and practitioners for fast prototyping and experimentation. Texar was originally developed and is actively contributed by Petuum and CMU in collaboration with other institutes. A mirror of this repository is maintained by Petuum Open Source. Two Versions, (Mostly) Same Interfaces. Texar-TensorFlow (this repo) and Texar-PyTorch have mostly the same interfaces. Both further combine the best design of TF and PyTorch. Rich Pre-trained Models, Rich Usage with Uniform Interfaces. BERT, GPT2, XLNet, etc, for encoding, classification, generation, and composing complex models with other Texar components!

trlX is a distributed training framework designed from the ground up to focus on fine-tuning large language models with reinforcement learning using either a provided reward function or a reward-labeled dataset. Training support for Hugging Face models is provided by Accelerate-backed trainers, allowing users to fine-tune causal and T5-based language models of up to 20B parameters, such as facebook/opt-6.7b, EleutherAI/gpt-neox-20b, and google/flan-t5-xxl. For models beyond 20B parameters, trlX provides NVIDIA NeMo-backed trainers that leverage efficient parallelism techniques to scale effectively.

Trax is an end-to-end library for deep learning that focuses on clear code and speed. It is actively used and maintained in the Google Brain team. Run a pre-trained Transformer, create a translator in a few lines of code. Features and resources, API docs, where to talk to us, how to open an issue and more. Walkthrough, how Trax works, how to make new models and train on your own data. Trax includes basic models (like ResNet, LSTM, Transformer) and RL algorithms (like REINFORCE, A2C, PPO). It is also actively used for research and includes new models like the Reformer and new RL algorithms like AWR. Trax has bindings to a large number of deep learning datasets, including Tensor2Tensor and TensorFlow datasets. You can use Trax either as a library from your own python scripts and notebooks or as a binary from the shell, which can be more convenient for training large models. It runs without any changes on CPUs, GPUs and TPUs.

General purpose agents using reinforcement learning. Combines radial basis functions, temporal difference learning, planning, uncertainty estimations, and curiosity. Intended to be an out-of-the-box solution for roboticists and game developers.

A large crowd-sourced dataset for developing natural language interfaces for relational databases. WikiSQL is the dataset released along with our work Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning. Regarding tokenization and Stanza, when WikiSQL was written 3-years ago, it relied on Stanza, a CoreNLP python wrapper that has since been deprecated. If you'd still like to use the tokenizer, please use the docker image. We do not anticipate switching to the current Stanza as changes to the tokenizer would render the previous results not reproducible.

DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo. DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo physics. The MuJoCo Python bindings support three different OpenGL rendering backends: EGL (headless, hardware-accelerated), GLFW (windowed, hardware-accelerated), and OSMesa (purely software-based). At least one of these three backends must be available in order render through dm_control. Hardware rendering with a windowing system is supported via GLFW and GLEW. On Linux these can be installed using your distribution's package manager. "Headless" hardware rendering (i.e. without a windowing system such as X11) requires EXT_platform_device support in the EGL driver. While dm_control has been largely updated to use the pybind11-based bindings provided via the mujoco package, at this time it still relies on some legacy components that are automatically generated.

VERL is a reinforcement-learning–oriented toolkit designed to train and align modern AI systems, from language models to decision-making agents. It brings together supervised fine-tuning, preference modeling, and online RL into one coherent training stack so teams can move from raw data to aligned policies with minimal glue code. The library focuses on scalability and efficiency, offering distributed training loops, mixed precision, and replay/buffering utilities that keep accelerators busy. It ships with reference implementations of popular alignment algorithms and clear examples that make it straightforward to reproduce baselines before customizing. Data pipelines treat human feedback, simulated environments, and synthetic preferences as interchangeable sources, which helps with rapid experimentation. VERL is meant for both research and production hardening: logging, checkpointing, and evaluation suites are built in so you can track learning dynamics and regressions over time.