Arena
Reinforcement learning streamlined with the platform built for RLOps
Trusted by leading institutions
%20(1).png){kind=small}
Arena has significantly streamlined our RL development workflow, making training and deploying agents a breeze. The platform's hyperparameter tuning capabilities have dramatically accelerated our experimentation and improved the performance of our models.
> import agilerl
open-source v2 released. 10x faster training.
.svg)
Single-agent and Multi-agent Support
Train on-policy, off-policy, offline, multi-agent and contextual multi-armed bandits with unmatched speed and performance
Evolutionary Hyperparameter Optimization
Achieve automatic, optimal performance in a single training run through hyperparameter and neural network evolution
Distributed Training
Take full advantage of your entire compute stack for online and offline reinforcement learning with multi-GPU support
Hierarchical Skills
Solve complex problems by breaking down tasks into smaller, learnable sub-tasks with the AgileRLÂ Skills wrapper
Case studies
Discover how AgileRL is delivering value
Optimising Logistics Efficiency
Dramatically increasing utilisation and reducing training time for complex bin-packing with Decision Lab
Revolutionising Algorithmic Trading
Maximising returns from high-frequency trading with Maxvankekeren-IT
Advancing Robot Learning
Pushing the boundaries of multi-agent reinforcement learning with University of Minnesota