Skip to content

AgileRL Documentation

AgileRL Documentation

Introduction

Getting Started
Releases

Arena

Arena Client

Training

Evolutionary Hyperparameter Optimization
Off-Policy Training
On-Policy Training
Partially Observable Markov Decision Processes (POMDPs)
Offline Training
Multi-Agent Training
LLM Fine-Tuning
Contextual Multi-Armed Bandits
Distributed Training
Trainers
Evolvable Neural Networks
Creating Custom Algorithms
Debugging Reinforcement Learning

Observability

Metrics and Logging

Tutorials

Gymnasium Single-agent
PettingZoo Multi-agent
Hierarchical Skills
LLM Fine-Tuning
Contextual Multi-arm Bandits
- Iris with NeuralUCB
- PenDigits with NeuralTS
Creating Custom Networks
- Building a Dueling Distributional Q Network
- Integrating Architecture Mutations Into SimBa
Training on Arena
- PPO on a Custom Gym Environment
- GRPO on GSM8K

API

Algorithms
Arena
Components
Hyperparameter Optimization
- Mutation
- Tournament Selection
Logger
Metrics
Models
Modules
Networks
Population
Training
Rollouts
- On-Policy Rollout Functions
Utils
Vector
Wrappers

Development

GitHub
Discord
Contribute to AgileRL

ArenaClient¶

The main client for interacting with the Arena platform. Handles authentication, environment management, experiment submission, and agent deployment.

Arena manifest models

Copyright © 2023, AgileRL

Made with Sphinx and @pradyunsg's Furo