Fruit-Tree

../../_images/fruit-tree.gif

Action Space

Discrete(2)

Observation Shape

(2,)

Observation High

[63 63]

Observation Low

[0 0]

Reward Shape

(6,)

Reward High

[10. 10. 10. 10. 10. 10.]

Reward Low

[0. 0. 0. 0. 0. 0.]

Import

mo_gymnasium.make("fruit-tree-v0")

Description

Full binary tree of depth d=5,6 or 7. Every leaf contains a fruit with a value for the nutrients Protein, Carbs, Fats, Vitamins, Minerals and Water. From Yang et al. 2019.

Observation Space

Discrete space of size 2^d-1, where d is the depth of the tree.

Action Space

The agent can chose to go left or right at every node. The action space is therefore a discrete space of size 2.

Reward Space

Each leaf node contains a 6-dimensional vector containing the nutrients of the fruit. The agent receives a reward for each nutrient it collects.

Starting State

The agent starts at the root node (0, 0).

Episode Termination

The episode terminates when the agent reaches a leaf node.