Spaces¶

Space¶

class rl_coach.spaces.Space(shape: Union[int, tuple, list, numpy.ndarray], low: Union[None, int, float, numpy.ndarray] = -inf, high: Union[None, int, float, numpy.ndarray] = inf)[source]¶

A space defines a set of valid values

Parameters

shape – the shape of the space
low – the lowest values possible in the space. can be an array defining the lowest values per point, or a single value defining the general lowest values
high – the highest values possible in the space. can be an array defining the highest values per point, or a single value defining the general highest values

contains(val: Union[int, float, numpy.ndarray]) → bool[source]¶

Checks if value is contained by this space. The shape must match and all of the values must be within the low and high bounds.

Parameters: val – a value to check
Returns: True / False depending on if the val matches the space definition

is_valid_index(index: numpy.ndarray) → bool[source]¶

Checks if a given multidimensional index is within the bounds of the shape of the space

Parameters: index – a multidimensional index
Returns: True if the index is within the shape of the space. False otherwise

sample() → numpy.ndarray[source]¶

Sample the defined space, either uniformly, if space bounds are defined, or Normal distributed if no bounds are defined

Returns: A numpy array sampled from the space

Observation Spaces¶

class rl_coach.spaces.ObservationSpace(shape: Union[int, numpy.ndarray], low: Union[None, int, float, numpy.ndarray] = -inf, high: Union[None, int, float, numpy.ndarray] = inf)[source]¶

contains(val: Union[int, float, numpy.ndarray]) → bool¶

Checks if value is contained by this space. The shape must match and all of the values must be within the low and high bounds.

Parameters: val – a value to check
Returns: True / False depending on if the val matches the space definition

is_valid_index(index: numpy.ndarray) → bool¶

Checks if a given multidimensional index is within the bounds of the shape of the space

Parameters: index – a multidimensional index
Returns: True if the index is within the shape of the space. False otherwise

sample() → numpy.ndarray¶

Sample the defined space, either uniformly, if space bounds are defined, or Normal distributed if no bounds are defined

Returns: A numpy array sampled from the space

VectorObservationSpace¶

class rl_coach.spaces.VectorObservationSpace(shape: int, low: Union[None, int, float, numpy.ndarray] = -inf, high: Union[None, int, float, numpy.ndarray] = inf, measurements_names: List[str] = None)[source]¶: An observation space which is defined as a vector of elements. This can be particularly useful for environments which return measurements, such as in robotic environments.

PlanarMapsObservationSpace¶

class rl_coach.spaces.PlanarMapsObservationSpace(shape: numpy.ndarray, low: int, high: int, channels_axis: int = -1)[source]¶: An observation space which defines a stack of 2D observations. For example, an environment which returns a stack of segmentation maps like in Starcraft.

ImageObservationSpace¶

class rl_coach.spaces.ImageObservationSpace(shape: numpy.ndarray, high: int, channels_axis: int = -1)[source]¶: An observation space which is a private case of the PlanarMapsObservationSpace, where the stack of 2D observations represent a RGB image, or a grayscale image.

Action Spaces¶

class rl_coach.spaces.ActionSpace(shape: Union[int, numpy.ndarray], low: Union[None, int, float, numpy.ndarray] = -inf, high: Union[None, int, float, numpy.ndarray] = inf, descriptions: Union[None, List, Dict] = None, default_action: Union[int, float, numpy.ndarray, List] = None)[source]¶

clip_action_to_space(action: Union[int, float, numpy.ndarray, List]) → Union[int, float, numpy.ndarray, List][source]¶

Given an action, clip its values to fit to the action space ranges

Parameters: action – a given action
Returns: the clipped action

contains(val: Union[int, float, numpy.ndarray]) → bool¶

Checks if value is contained by this space. The shape must match and all of the values must be within the low and high bounds.

Parameters: val – a value to check
Returns: True / False depending on if the val matches the space definition

is_valid_index(index: numpy.ndarray) → bool¶

Checks if a given multidimensional index is within the bounds of the shape of the space

Parameters: index – a multidimensional index
Returns: True if the index is within the shape of the space. False otherwise

sample() → numpy.ndarray¶

Sample the defined space, either uniformly, if space bounds are defined, or Normal distributed if no bounds are defined

Returns: A numpy array sampled from the space

sample_with_info() → rl_coach.core_types.ActionInfo[source]¶

Get a random action with additional “fake” info

Returns: An action info instance

AttentionActionSpace¶

class rl_coach.spaces.AttentionActionSpace(shape: int, low: Union[None, int, float, numpy.ndarray] = -inf, high: Union[None, int, float, numpy.ndarray] = inf, descriptions: Union[None, List, Dict] = None, default_action: numpy.ndarray = None, forced_attention_size: Union[None, int, float, numpy.ndarray] = None)[source]¶: A box selection continuous action space, meaning that the actions are defined as selecting a multidimensional box from a given range. The actions will be in the form: [[low_x, low_y, …], [high_x, high_y, …]]

BoxActionSpace¶

class rl_coach.spaces.BoxActionSpace(shape: Union[int, numpy.ndarray], low: Union[None, int, float, numpy.ndarray] = -inf, high: Union[None, int, float, numpy.ndarray] = inf, descriptions: Union[None, List, Dict] = None, default_action: numpy.ndarray = None)[source]¶: A multidimensional bounded or unbounded continuous action space

DiscreteActionSpace¶

class rl_coach.spaces.DiscreteActionSpace(num_actions: int, descriptions: Union[None, List, Dict] = None, default_action: numpy.ndarray = None, filtered_action_space=None)[source]¶: A discrete action space with action indices as actions

MultiSelectActionSpace¶

class rl_coach.spaces.MultiSelectActionSpace(size: int, max_simultaneous_selected_actions: int = 1, descriptions: Union[None, List, Dict] = None, default_action: numpy.ndarray = None, allow_no_action_to_be_selected=True)[source]¶: A discrete action space where multiple actions can be selected at once. The actions are encoded as multi-hot vectors

CompoundActionSpace¶

class rl_coach.spaces.CompoundActionSpace(sub_spaces: List[rl_coach.spaces.ActionSpace])[source]¶: An action space which consists of multiple sub-action spaces. For example, in Starcraft the agent should choose an action identifier from ~550 options (Discrete(550)), but it also needs to choose 13 different arguments for the selected action identifier, where each argument is by itself an action space. In Starcraft, the arguments are Discrete action spaces as well, but this is not mandatory.

Goal Spaces¶

class rl_coach.spaces.GoalsSpace(goal_name: str, reward_type: rl_coach.spaces.GoalToRewardConversion, distance_metric: Union[rl_coach.spaces.GoalsSpace.DistanceMetric, Callable])[source]¶

A multidimensional space with a goal type definition. It also behaves as an action space, so that hierarchical agents can use it as an output action space. The class acts as a wrapper to the target space. So after setting the target space, all the values of the class will match the values of the target space (the shape, low, high, etc.)

Parameters

goal_name – the name of the observation space to use as the achieved goal.
reward_type – the reward type to use for converting distances from goal to rewards
distance_metric – the distance metric to use. could be either one of the distances in the DistanceMetric enum, or a custom function that gets two vectors as input and returns the distance between them

class DistanceMetric[source]¶: An enumeration.

clip_action_to_space(action: Union[int, float, numpy.ndarray, List]) → Union[int, float, numpy.ndarray, List]¶

Given an action, clip its values to fit to the action space ranges

Parameters: action – a given action
Returns: the clipped action

contains(val: Union[int, float, numpy.ndarray]) → bool¶

Checks if value is contained by this space. The shape must match and all of the values must be within the low and high bounds.

Parameters: val – a value to check
Returns: True / False depending on if the val matches the space definition

distance_from_goal(goal: numpy.ndarray, state: dict) → float[source]¶

Given a state, check its distance from the goal

Parameters

goal – a numpy array representing the goal
state – a dict representing the state

Returns

the distance from the goal

get_reward_for_goal_and_state(goal: numpy.ndarray, state: dict) → Tuple[float, bool][source]¶

Given a state, check if the goal was reached and return a reward accordingly

Parameters

goal – a numpy array representing the goal
state – a dict representing the state

Returns

the reward for the current goal and state pair and a boolean representing if the goal was reached

goal_from_state(state: Dict)[source]¶

Given a state, extract an observation according to the goal_name

Parameters: state – a dictionary of observations
Returns: the observation corresponding to the goal_name

is_valid_index(index: numpy.ndarray) → bool¶

Checks if a given multidimensional index is within the bounds of the shape of the space

Parameters: index – a multidimensional index
Returns: True if the index is within the shape of the space. False otherwise

sample() → numpy.ndarray¶

Sample the defined space, either uniformly, if space bounds are defined, or Normal distributed if no bounds are defined

Returns: A numpy array sampled from the space

sample_with_info() → rl_coach.core_types.ActionInfo¶

Get a random action with additional “fake” info

Returns: An action info instance