# ExploreRL — On-Device RL Training

> On-Device RL Training (iPhone/iPad app by Justin Daludado.)

- Source: https://appshunter.io/ios/app/explorerl/id6758944321 (this page in markdown: same URL + `.md`)
- Developer: [Justin Daludado](https://appshunter.io/developer/1779347505)
- Category: Developer Tools, Education
- Price: Free
- Age rating: 4+
- Requires: iOS 18.0 · 25 MB
- Languages: English
- Released: 2026-02-11
- Data updated: 2026-07-09
- User reviews in markdown: https://appshunter.io/ios/app/explorerl/id6758944321/reviews.md

## What is ExploreRL?

Train, visualize, and experiment with Reinforcement Learning algorithms entirely on-device with ExploreRL.

Built with MLX, ExploreRL provides an interactive sandbox to test various environments and algorithms with different hyperparameters to observe how RL agents learn through trial and error.

LEARN BY DOING

Train agents on classic adapted environments and observe learning in real time. Watch values grow, track reward curves, and develop intuition for how different algorithms and hyperparameters affect performance. Read and learn about reinforcement learning concepts in the documentation.

ALGORITHMS
Four common implementations:

- Q-Learning 
- SARSA
- Deep Q-Network (DQN) for discrete action spaces
- Soft Actor-Critic (SAC) for continuous control

INCLUDED ENVIRONMENTS
Adapted from classic standards:

Toy Text: Frozen Lake, Blackjack, Taxi, Cliff Walking
Classic Control: CartPole, Mountain Car, Mountain Car Continuous, Acrobot, Pendulum
Box2D: Lunar Lander, Lunar Lander Continuous, Car Racing, Car Racing Discrete

FEATURES

- Environment-specific settings
- Real-time training metrics and reward visualization
- Configurable hyperparameters: learning rate, discount factor, epsilon decay, batch size
- Agent library with save, load, duplicate, and export functionality
- Evaluation mode to test trained agents without further training
- Educational documentation covering RL concepts, neural networks, and algorithms
- Custom seed for reproducibility

Note: Training performance will vary by device. Devices with newer hardware and more memory will have a better experience.


## Version history (last 4 releases)

### 2.0 — 2026-06-29

- fixed several bugs and crashes
- updated layouts
- performance fixes
- updated Explore content
- updated navigation

### 1.1.0 — 2026-03-09

Quality of life changes:
- fix several UI issues
- fix various bugs
- better device info in settings
- add option to train different environments at once
- fix import/export lag
- quick open saved agent files
- ability to rename saved sessions

### 1.0.1 — 2026-02-23

- fixed an issue where files were incorrectly exported
- fix performance issues in some environments 
- updated list designs

### 1.0 — 2026-02-12

No release notes.

## More apps by Justin Daludado

- [don't secure me](https://appshunter.io/ios/app/dont-secure-me/id6738100050)
- [NextMove](https://appshunter.io/ios/app/nextmove/id6752559277)

All apps by Justin Daludado: https://appshunter.io/developer/1779347505

---

*Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-07-09.*