TronGridEnvironment¶

class colosseumrl.envs.tron.TronGridEnvironment.TronGridEnvironment(config: str = '')[source]¶

STRING_TO_ACTION = {'': 0, 'forward': 0, 'left': -1, 'right': 1}¶

static create(board_size: int = 20, num_players: int = 4, observation_window: int = -1, remove_on_death: bool = False) → colosseumrl.envs.tron.TronGridEnvironment.TronGridEnvironment[source]¶

Secondary constructor with explicit options for creating the environment

Parameters

board_size (int) – This will specify the square size of the playing grid.
num_players (int) – Number of active players in the game.
observation_window (-1) – Current not used
remove_on_death (bool) – Whether or not to remove the player and their associated walls when they are eliminated.

static deserialize_state(serialized_state: bytearray) → object[source]¶

Convert a serialized bytearray back into a game state.

Parameters: serialized_state (bytearray) – Serialized byte-string for the state.
Returns: The current game state.
Return type: object

is_valid_action(state: object, player: int, action: str) → bool[source]¶

Whether or not an action is valid for a specific state.

Parameters

state (object) – The current state of the game.
player (int) – The player who is executing this action.
action (str) – The action the player is executing.

Returns

Whether or not this is a valid action in the current state. This is always true for tron as every action is valid.

Return type

bool

property max_players¶

Property holding the number of players present required to play game.

Returns: The specified number of players in this game.
Return type: int

property min_players¶

Property holding the number of players present required to play game.

Returns: The specified number of players in this game.
Return type: int

new_state(num_players: int = None) → Tuple[object, List[int]][source]¶

Create an initial tron state.

Parameters

num_players (int, optional.) – The number of players for the game. Note, this option gets ignored here in favor of the global player configuration when creating the environment.

Returns

State (Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]) – The full state of the new tron environment.
player_list (List[int]) – Which players are currently acting.

next_state(state: object, players: [<class 'int'>], actions: [<class 'str'>])[source]¶

Compute a single step in the game.

Notes

Player numbers must be numbers in the set {0, 1, …, n-1} for an n player game.

Parameters

state (Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]) – The current state of the game.
players ([int]) – The players which are taking the given actions.
actions ([str]) – The actions of each player.

Returns

new_state (object) – The new state of the game.
new_players (List[int]) – List of players who’s turn it is in the new state now.
rewards (List[float]) – The reward for each player that acted.
terminal (bool) – Whether or not the game has ended.
winners (List[int]) – If the game has ended, who are the winners.

static observation_names() → List[str][source]¶

Static method for returning the names of the observation objects.

Returns: The keys of the observation dictionary.
Return type: List[str]

property observation_shape¶

Describe the fixed numpy shapes of each observation.

Returns: The shape, as a tuple, of each numpy array by their name.
Return type: Dict[str, Tuple[int]]

static serializable() → bool[source]¶

Whether or not this class supports serialization of the state.

Returns: False, Tron doesnt need to be serializable as the state is current fully observable.
Return type: bool

static serialize_state(state: object) → bytearray[source]¶

Serialize a game state and convert it to a bytearray to be saved or sent over a network.

Parameters: state (object) – The current game state.
Returns: Serialized byte-string for the state.
Return type: bytearray

state_to_observation(state: object, player: int) → Dict[str, numpy.ndarray][source]¶

Convert the raw game state to the observation for the agent. Maps each observation name into an observation.

Parameters

state (object) – The full server state of the game.
player (int) – Which player is getting the observation.

Returns

The observation dictionary with keys equal to the observation_names above.

Return type

Dict[str, np.ndarray]