Interactive Demo WebApp

See elsci.org for more information

Applications

Select Application:

Local Config:

Observed State Input:

Select Analysis File:

Agent Type

Q-Learning

Deep Q-Network

Training Configuration

Training Episodes:

Training Repeats (fixed starting position):

Training Seeds (random starting position):

Testing Configuration

Test Episodes:

Test Repeats:

Q-Learning Parameters

Learning Rate (Alpha):

Discount Factor (Gamma):

Exploration Rate (Epsilon):

Epsilon Step:

DQN Parameters

Input Size:

Sentence Hidden Dimension:

Hidden Dimension:

Number of Hidden Layers:

Sequence Size:

Memory Size:

Target Replace Iterations:

Learning Rate:

Batch Size:

User Input

🚀

What the agent see to match with your input instructions

Was the result correct?

Select Preview Image: