gold_explorer

Functions

prt_sim.jhu.gold_explorer.get_state_index(x, y, z)

Classes

class prt_sim.jhu.gold_explorer.GoldExplorer(render_mode: str | None = 'rgb_array')

The Gold Explorer puzzle

Action space: integer representing a discrete action described in the table below

Num	Action
0	North
1	East
2	South
3	West

Observation space: integer between 0 and 127 representing the state as an octal number, <gold bit><row><column>

Reward: +15 for obtaining gold coins, +30 for obtaining the motherlode, -30 for entering a mine field, -1 for every other location

execute_action(action: int) → Tuple[int, float, bool]

Executes an action for the explorer.

Parameters:

action (int) – the action to execute

Returns:

get_number_of_actions() → int

Returns the number of discrete actions in the puzzle

Returns:

total number of actions in the puzzle

Return type:

int

get_number_of_states() → int

Returns the number of states in the puzzle

Returns:

total number of states in the puzzle

Return type:

int

render()

Renders the environment

reset(seed: int | None = None, randomize_start: bool | None = False) → int

Resets the environment to the initial state.

Parameters:

• seed (int, optional) – Random seed. Defaults to None.

• randomize_start (bool, optional) – Whether to randomize the starting state. Not all environments will support this. Defaults to False.

Returns:

current state value

Return type:

int