Watch a robot learn to work a warehouse floor

Pick and deliver across a warehouse floor. Press start and watch an untrained robot become an efficient router.

Results
Items delivered
—
after you train
Completion rate
after you train
Routing efficiency
after you train
Algorithm
PPO
Model Performance Rating

No training completed yet

N/A
Delivery efficiency
Pickups
—
—
Drop-offs
—
—
Delivered
—
—

after you train

Session history
All sessions
Loading…
Evaluation history
Full page

Select a session to list replay runs.

Warehouse robot2D
episode 1 · step 0 · 0 fps

This is a live preview while the robot learns. Head to Replay to watch the fully trained robot in action.

Loading warehouse map…
Robot Status
Action
—
Training progress
0%
Status
—
Elapsed
0:00
Algorithm
ppo
Robot
PARKED
Reward
—
Carry
0
Delivered
0/0
Shelf
—
Dock
—
Remaining
0
1. Configure
steps

Editable anytime before Start.

~1-2 min · good default for most runs

Same idea, real warehouses

This is the same kind of adaptive learning OptRL uses to cut picking time, reduce idle travel, and raise throughput in live fulfillment centers, without rebuilding what you already run.

Frequently Asked Questions

Common questions about the warehouse adaptive learning demo

An interactive simulation where you can watch a reinforcement learning agent learn to pick up items and deliver them in a warehouse, improving with each attempt.

A type of AI training where an agent improves its decisions through trial, error, and reward, similar to how a robot here learns faster delivery routes the more it practices. This is also known as adaptive learning.

No. Press "Start Training" and watch the results. No code or RL experience is required.

The same reinforcement learning techniques shown here are used by OptRL to optimize picking routes, reduce travel distance, and improve throughput in real fulfillment centers.

Yes — the OptRL playground includes other simulations beyond the warehouse, each showing reinforcement learning applied to a different real-world operation.

See how this applies to your warehouse.

Or try another environment in the full playground.

Explore the full playground →