Sourcify
Effortlessly find and manage open-source dependencies for your projects.

An open-source library for reinforcement learning, offering scalable and fault-tolerant RL workloads.

RLlib is an open-source library built on Ray for reinforcement learning. It provides scalable and fault-tolerant RL workloads with unified APIs for various industry applications, including multi-agent setups, offline data training, and simulator integration. The architecture supports distributed sample collection via EnvRunner actors, loss calculation, and model updating. RLlib integrates with Ray Data for large-scale data ingestion for offline RL and behavior cloning. It supports customization through the RLModule APIs, enabling complex multi-model setups and component sharing between agents. RLlib also provides APIs for compiling and executing accelerated DAGs.
RLlib is an open-source library built on Ray for reinforcement learning.
Explore all tools that specialize in behavior cloning. This domain focus ensures RLlib delivers optimized results for this specific requirement.
Utilizes EnvRunner actors to parallelize data collection from multiple environments, configurable via `config.env_runners(num_env_runners=...)`.
Supports multi-GPU training through Learner actors, configurable with `config.learners(num_learners=...)` and `config.learners(num_gpus_per_learner=1)`.
Provides native support for MARL, allowing the implementation of independent, collaborative, and adversarial training scenarios.
Integrates with Ray Data for large-scale data ingestion, enabling offline RL and behavior cloning workloads.
Supports connecting external RL environments through custom EnvRunner logic, allowing integration with TCP-connected environments and external action inference using ONNX.
Install Ray with RLlib: `pip install "ray[rllib]" torch`
Install Gymnasium for environment support: `pip install "gymnasium[atari,accept-rom-license,mujoco]"`
Create a configuration for the RL algorithm using `PPOConfig()` or similar.
Define the RL environment using `config.environment("EnvironmentName")`.
Build the algorithm using `config.build_algo()`.
Train the algorithm for a specified number of iterations using `algo.train()`.
Evaluate the trained algorithm using `algo.evaluate()`.
Release resources using `algo.stop()`.
All Set
Ready to go
Verified feedback from other users.
"RLlib is highly regarded for its scalability, flexibility, and support for complex RL scenarios."
Post questions, share tips, and help other users.
Effortlessly find and manage open-source dependencies for your projects.

End-to-end typesafe APIs made easy.

Page speed monitoring with Lighthouse, focusing on user experience metrics and data visualization.

Topcoder is a pioneer in crowdsourcing, connecting businesses with a global talent network to solve technical challenges.

Explore millions of Discord Bots and Discord Apps.

Build internal tools 10x faster with an open-source low-code platform.

Open-source RAG evaluation tool for assessing accuracy, context quality, and latency of RAG systems.

AI-powered synthetic data generation for software and AI development, ensuring compliance and accelerating engineering velocity.