rlgt.environments.linear_environments.LinearFlipEnvironment

class documentation

class LinearFlipEnvironment(GraphEnvironment):

Constructor: LinearFlipEnvironment(graph_invariant, graph_order, flattened_ordering, is_directed, ...)

This class inherits from the GraphEnvironment class and models a graph building game for constructing 2-edge-colored looped complete graphs. The edges (resp. arcs) are initially fully colored in some manner and can then be potentially flipped one by one in either row-major or clockwise order. Users can configure the graph order, whether the graphs are directed or undirected, whether loops are allowed, and the mechanism used to generate the initial fully colored graphs, which may be deterministic or nondeterministic. The flipping of edges (resp. arcs) follows the reconstruction from a flattened format: if loops are not allowed, the corresponding edges are ignored, and if the graphs are undirected, only the upper-triangular part of the adjacency matrix is considered (including or excluding the diagonal depending on loop allowance), so each edge is flipped in both directions simultaneously. The user can select whether edges (resp. arcs) are flipped in row-major or clockwise order.

The RL tasks in this environment are episodic, and the episode length equals the flattened length, i.e., the number of entries in either flattened format with color numbers. This length depends on the graph order, whether the graphs are directed, and whether loops are allowed.

Each state is represented by a binary numpy.ndarray vector of type numpy.uint8 and length 2 * flattened_length, where flattened_length is the flattened length of the graphs. In the state vectors, the first flattened_length bits indicate which edges (resp. arcs) are currently colored with color 1, while the final flattened_length bits form a one-hot encoding of the edge (resp. arc) to be potentially flipped next. A 1 at a given position identifies the next edge (resp. arc) to potentially flip, while all zeros indicate a terminal state in which all edges (resp. arcs) have been traversed.

Each action is represented by a numpy.int32 integer, either 0 or 1. The value 1 flips the color of the next edge (resp. arc), while 0 leaves it unchanged.

Method	`__init__`	This constructor initializes an instance of the `LinearFlipEnvironment` class.
Method	`state_batch_to_graph_batch`	This abstract method must be implemented by any concrete subclass. It extracts the batch of underlying graphs corresponding to a provided batch of states. Implementations must return a `Graph` object containing the graphs corresponding to each row in ...
Instance Variable	`initial_graph_generator`	A `GraphGenerator` function that defines how the underlying fully colored graphs are generated for the initial states. This attribute may be reconfigured between independent batches of episodes.
Property	`action_mask`	This abstract property must be implemented by any concrete subclass. It must return `None` if no episodes are currently being run in parallel, or if every action is available in every current state. Otherwise, it must return a two-dimensional ...
Property	`action_number`	This abstract property must be implemented by any concrete subclass. It must return the total number of distinct actions that can be executed in the environment, as a positive `int`.
Property	`episode_length`	This abstract property must be implemented by any concrete subclass. It must return the predetermined common length of all episodes run in parallel, i.e., the total number of actions executed in each episode, as a positive ...
Property	`is_continuing`	This abstract property must be implemented by any concrete subclass. It must return a `bool` indicating whether the environment is continuing (`True`) or episodic (`False`).
Property	`state_dtype`	This abstract property must be implemented by any concrete subclass. It must return the data type of the one-dimensional `numpy.ndarray` vectors that represent states, as a `numpy.dtype`.
Property	`state_length`	This abstract property must be implemented by any concrete subclass. It must return the number of entries in each state vector, i.e., the length of the one-dimensional `numpy.ndarray` vectors that represent states, as a positive ...
Method	`_initialize_batch`	This abstract method must be implemented by any concrete subclass. It must initialize a batch of episodes of the specified size and update the `_state_batch` and `_status` attributes so that they represent the newly initialized batch.
Method	`_transition_batch`	This abstract method must be implemented by any concrete subclass. It must apply a batch of actions to the current batch of states and update the `_state_batch` and `_status` attributes to reflect the resulting states and the updated batch status...
Instance Variable	`_allow_loops`	A `bool` indicating whether loops are allowed in the graphs to be constructed.
Instance Variable	`_flattened_length`	A positive `int` equal to the flattened length of the graphs to be constructed, which also equals the total number of steps needed to reach a terminal state.
Instance Variable	`_flattened_ordering`	An item of the `FlattenedOrdering` enumeration specifying whether the edges (resp. arcs) are potentially flipped in row-major or clockwise order.
Instance Variable	`_is_directed`	A `bool` indicating whether the graphs to be constructed are directed or undirected.
Instance Variable	`_state_batch`	See the description of the `GraphEnvironment._state_batch` attribute.
Instance Variable	`_status`	See the description of the `GraphEnvironment._status` attribute.
Instance Variable	`_step_count`	Either `None` or a nonnegative `int` between 0 and `_flattened_length` indicating the index of the next edge (resp. arc) to potentially flipped according to `_flattened_ordering`. When `_step_count` equals `_flattened_length`...

Inherited from GraphEnvironment:

Method	`reset_batch`	This method initializes a batch of episodes of a specified size and returns the resulting batch of states, the corresponding values of the selected graph invariant (if computed), and the status of the batch of episodes...
Method	`state_to_graph`	This method extracts the underlying graph corresponding to a single state.
Method	`step_batch`	This method applies a batch of actions to the current batch of episodes and returns the resulting batch of states, the corresponding values of the selected graph invariant (if computed), and the updated status of the batch...
Instance Variable	`sparse_setting`	A `bool` indicating whether the graph invariant values should be computed only for the final batch of actions.
Instance Variable	`__graph_batch`	Either `None` or a `Graph` object representing the current batch of underlying graphs. This attribute is updated only when required by the sparse setting.
Instance Variable	`__graph_invariant`	A `GraphInvariant` function specifying the graph invariant to be maximized.
Instance Variable	`__graph_invariant_batch`	Either `None` or a one-dimensional `numpy.ndarray` of type `numpy.float32` containing the current batch of graph invariant values. As with `__graph_batch`, this attribute is updated only when required by the sparse setting.
Instance Variable	`__graph_invariant_diff`	Either `None`, indicating that graph invariant values are always computed directly using `__graph_invariant`, or a `GraphInvariantDiff` function used to incrementally update invariant values after state transitions.

def __init__(self, graph_invariant: GraphInvariant, graph_order: int, flattened_ordering: FlattenedOrdering = FlattenedOrdering.ROW_MAJOR, is_directed: bool = False, allow_loops: bool = False, initial_graph_generator: GraphGenerator | None = None, graph_invariant_diff: GraphInvariantDiff | None = None, sparse_setting: bool = False): ¶

overrides rlgt.environments.graph_environment.GraphEnvironment.__init__

This constructor initializes an instance of the LinearFlipEnvironment class.

Parameters
graph_invariant:`GraphInvariant`	A `GraphInvariant` function that computes the graph invariant values associated with a batch of underlying graphs. These values are the quantities to be maximized by the environment.
graph_order:`int`	A positive `int` (not below 2) that represents the graph order of the graphs to be constructed.
flattened_ordering:`FlattenedOrdering`	An item of the `FlattenedOrdering` enumeration indicating whether the edges (resp. arcs) should be potentially flipped in the row-major or clockwise order. The default value is `FlattenedOrdering.ROW_MAJOR`.
is_directed:`bool`	A `bool` indicating whether the graphs to be constructed are directed. The default value is `False`.
allow_loops:`bool`	A `bool` indicating whether loops are allowed in the graphs to be constructed. The default value is `False`.
initial_graph_generator:`GraphGenerator \| None`	Either `None` or a `GraphGenerator` function that determines how the initial fully colored graphs are generated for the batch of initial states. If `None`, all edges (resp. arcs) in all graphs are initially colored with color 0. The default value is `None`.
graph_invariant_diff:`GraphInvariantDiff \| None`	Either `None`, indicating that graph invariant values are always computed directly using `graph_invariant`, or a `GraphInvariantDiff` function that computes element-wise differences of the graph invariant values when the environment transitions from one batch of underlying graphs to another. The default value is `None`.
sparse_setting:`bool`	A `bool` indicating whether the sparse setting is enabled. If set to `True`, the graph invariant values are computed only for the final batch of actions. Otherwise, the graph invariant values are computed after every batch of actions. The default value is `False`.

def state_batch_to_graph_batch(self, state_batch: np.ndarray) -> Graph: ¶

overrides rlgt.environments.graph_environment.GraphEnvironment.state_batch_to_graph_batch

This abstract method must be implemented by any concrete subclass. It extracts the batch of underlying graphs corresponding to a provided batch of states. Implementations must return a Graph object containing the graphs corresponding to each row in state_batch, preserving the row order. This method must be pure and must not modify any attributes of the class instance.

Parameters
state_batch:`np.ndarray`	A two-dimensional `numpy.ndarray` whose rows represent individual states from which the underlying graphs are to be extracted.

Returns
`Graph`	A `Graph` object representing the extracted batch of graphs.

initial_graph_generator: GraphGenerator = ¶

A GraphGenerator function that defines how the underlying fully colored graphs are generated for the initial states. This attribute may be reconfigured between independent batches of episodes.

@property

action_mask: np.ndarray | None = ¶

overrides rlgt.environments.graph_environment.GraphEnvironment.action_mask

This abstract property must be implemented by any concrete subclass. It must return None if no episodes are currently being run in parallel, or if every action is available in every current state. Otherwise, it must return a two-dimensional numpy.ndarray matrix a of type bool whose entry a[i, j] is True if and only if action j is available in the current state of the i-th episode.

@property

action_number: int = ¶

overrides rlgt.environments.graph_environment.GraphEnvironment.action_number

This abstract property must be implemented by any concrete subclass. It must return the total number of distinct actions that can be executed in the environment, as a positive int.

@property

episode_length: int = ¶

overrides rlgt.environments.graph_environment.GraphEnvironment.episode_length

This abstract property must be implemented by any concrete subclass. It must return the predetermined common length of all episodes run in parallel, i.e., the total number of actions executed in each episode, as a positive int.

@property

is_continuing: bool = ¶

overrides rlgt.environments.graph_environment.GraphEnvironment.is_continuing

This abstract property must be implemented by any concrete subclass. It must return a bool indicating whether the environment is continuing (True) or episodic (False).

@property

state_dtype: np.dtype = ¶

overrides rlgt.environments.graph_environment.GraphEnvironment.state_dtype

This abstract property must be implemented by any concrete subclass. It must return the data type of the one-dimensional numpy.ndarray vectors that represent states, as a numpy.dtype.

@property

state_length: int = ¶

overrides rlgt.environments.graph_environment.GraphEnvironment.state_length

This abstract property must be implemented by any concrete subclass. It must return the number of entries in each state vector, i.e., the length of the one-dimensional numpy.ndarray vectors that represent states, as a positive int.

def _initialize_batch(self, batch_size: int): ¶

overrides rlgt.environments.graph_environment.GraphEnvironment._initialize_batch

This abstract method must be implemented by any concrete subclass. It must initialize a batch of episodes of the specified size and update the _state_batch and _status attributes so that they represent the newly initialized batch.

Parameters
batch_size:`int`	The number of episodes to initialize in the batch, given as a positive `int`.

def _transition_batch(self, action_batch: np.ndarray): ¶

overrides rlgt.environments.graph_environment.GraphEnvironment._transition_batch

This abstract method must be implemented by any concrete subclass. It must apply a batch of actions to the current batch of states and update the _state_batch and _status attributes to reflect the resulting states and the updated batch status. Implementations may also update additional subclass-specific attributes as required.

Parameters
action_batch:`np.ndarray`	A one-dimensional `numpy.ndarray` of type `numpy.int32` containing the actions to be applied. The length of `action_batch` must match the number of states in `_state_batch`.

_allow_loops: bool = ¶

A bool indicating whether loops are allowed in the graphs to be constructed.

_flattened_length: int = ¶

A positive int equal to the flattened length of the graphs to be constructed, which also equals the total number of steps needed to reach a terminal state.

_flattened_ordering: FlattenedOrdering = ¶

An item of the FlattenedOrdering enumeration specifying whether the edges (resp. arcs) are potentially flipped in row-major or clockwise order.

_is_directed: bool = ¶

A bool indicating whether the graphs to be constructed are directed or undirected.

_state_batch = ¶

overrides rlgt.environments.graph_environment.GraphEnvironment._state_batch

See the description of the GraphEnvironment._state_batch attribute.

_status = ¶

overrides rlgt.environments.graph_environment.GraphEnvironment._status

See the description of the GraphEnvironment._status attribute.

_step_count: int | None = ¶

Either None or a nonnegative int between 0 and _flattened_length indicating the index of the next edge (resp. arc) to potentially flipped according to _flattened_ordering. When _step_count equals _flattened_length, the state is terminal. This attribute is initially None and updated after each call to GraphEnvironment.reset_batch or GraphEnvironment.step_batch.