The Beginner's RL Playground

Algorithm Settings

Algorithm:

Exploration Strategy:

Learning Rate (α):

0.1

Actor LR (α_A):

0.1

Critic LR (α_C):

0.1

SR Matrix LR (α_M):

0.1

SR Weight LR (α_W):

0.1

Discount Factor (γ):

0.9

Exploration Rate (ε):

0.2

Softmax Temperature (β):

1.0

Interactive Simulation

Tip: Click to cycle state content (💎/☠️/🚧/empty).
Shift+Click to set start state (🏠).

Environment Settings

Grid Size:

Cell Display:

Step Penalty:

-0.1

Gem Reward:

Skull Penalty:

-10

Max Steps / Episode:

100

Speed:

750

Terminate on Reward

Action Values Q(s,a)

↑ 0.00

← 0.00

→ 0.00

↓ 0.00

Action Probabilities π(a | s)

↑ 0.25

← 0.25

→ 0.25

↓ 0.25

Algorithm Settings

Interactive Simulation

Environment Settings

Action Values Q(s,a)

Action Probabilities π(a | s)

Learning Progress Plot