SparsePomdp

class SparsePomdp[ValueType](other_model: stormpy.models.SparsePomdp[ValueType])

class SparsePomdp[ValueType](components, canonic_flag: bool = False)

POMDP in sparse representation

Template arguments:

• ValueType (type)

Available specializations:

• SparsePomdp[float]

• SparsePomdp[stormpy.numbers.Rational]

• SparsePomdp[stormpy.numbers.Interval]

• SparsePomdp[stormpy.numbers.RationalFunction]

• SparsePomdp[stormpy.numbers.RationalInterval]

Construction

The specialization can be inferred from the first positional constructor argument (alternatively, the components or other_model keyword argument).

Members

SparsePomdp.add_reward_model(self: stormpy.models.SparseModel[ValueType], arg0: str, arg1) → None

SparsePomdp.apply_scheduler(

self: stormpy.models.SparseMdp[ValueType],

scheduler,

drop_unreachable_states: bool = True,

) → stormpy.models.SparseModel[ValueType]

apply scheduler

property SparsePomdp.backward_transition_matrix

Backward transition matrix

property SparsePomdp.choice_labeling

get choice labelling

property SparsePomdp.choice_origins

SparsePomdp.collect_all_parameters(

self: stormpy.models.SparseModel[stormpy.numbers.RationalFunction],

) → set[stormpy.numbers.Variable]

Available only for: SparsePomdp[stormpy.numbers.RationalFunction].

Collect all parameters

SparsePomdp.collect_probability_parameters(

self: stormpy.models.SparseModel[stormpy.numbers.RationalFunction],

) → set[stormpy.numbers.Variable]

Available only for: SparsePomdp[stormpy.numbers.RationalFunction].

Collect probability parameters

SparsePomdp.collect_rate_parameters(

self: stormpy.models.SparseModel[stormpy.numbers.RationalFunction],

) → set[stormpy.numbers.Variable]

Available only for: SparsePomdp[stormpy.numbers.RationalFunction].

Collect rate parameters

SparsePomdp.collect_reward_parameters(

self: stormpy.models.SparseModel[stormpy.numbers.RationalFunction],

) → set[stormpy.numbers.Variable]

Available only for: SparsePomdp[stormpy.numbers.RationalFunction].

Collect reward parameters

SparsePomdp.get_choice_index(

self: stormpy.models.SparseMdp[ValueType],

state: SupportsInt | SupportsIndex,

action_offset: SupportsInt | SupportsIndex,

) → int

gets the choice index for the offset action from the given state.

SparsePomdp.get_labels_of_state(

self: stormpy.models.SparseModel[ValueType],

state: SupportsInt | SupportsIndex,

) → set[str]

Get labels of state

SparsePomdp.get_nr_available_actions(

self: stormpy.models.SparseMdp[ValueType],

state: SupportsInt | SupportsIndex,

) → int

SparsePomdp.get_observation(

self: stormpy.models.SparsePomdp[ValueType],

state: SupportsInt | SupportsIndex,

) → int

SparsePomdp.get_reward_model(self: stormpy.models.SparseModel[ValueType], name: str)

Reward model

SparsePomdp.get_states_with_parameter(

self: stormpy.models.SparseModel[stormpy.numbers.RationalFunction],

parameter: stormpy.numbers.Variable,

) → stormpy.datastructures.BitVector

Available only for: SparsePomdp[stormpy.numbers.RationalFunction].

Find states with a particular parameter

SparsePomdp.has_choice_labeling(self: stormpy.models.SparseModel[ValueType]) → bool

Does the model have an associated choice labelling?

SparsePomdp.has_choice_origins(self: stormpy.models.SparseModel[ValueType]) → bool

has choice origins?

SparsePomdp.has_observation_valuations(self: stormpy.models.SparsePomdp[ValueType]) → bool

property SparsePomdp.has_parameters

Flag whether model has parameters

SparsePomdp.has_reward_model(self: stormpy.models.SparseModel[ValueType], name: str) → bool

SparsePomdp.has_state_valuations(self: stormpy.models.SparseModel[ValueType]) → bool

has state valuation?

property SparsePomdp.initial_states

Initial states

property SparsePomdp.initial_states_as_bitvector

property SparsePomdp.is_discrete_time_model

Flag whether the model is a discrete time model

property SparsePomdp.is_exact

Flag whether model is exact

property SparsePomdp.is_nondeterministic_model

Flag whether the model contains nondeterminism

property SparsePomdp.is_partially_observable

Flag whether the model has observation labels

SparsePomdp.is_sink_state(

self: stormpy.models.SparseModel[ValueType],

state: SupportsInt | SupportsIndex,

) → bool

property SparsePomdp.is_sparse_model

Flag whether the model is stored as a sparse model

property SparsePomdp.is_symbolic_model

Flag whether the model is stored using decision diagrams

property SparsePomdp.labeling

Labels

property SparsePomdp.model_type

Model type

property SparsePomdp.nondeterministic_choice_indices

property SparsePomdp.nr_choices

Number of choices

property SparsePomdp.nr_observations

property SparsePomdp.nr_states

Number of states

property SparsePomdp.nr_transitions

Number of transitions

property SparsePomdp.observation_valuations

property SparsePomdp.observations

SparsePomdp.reduce_to_state_based_rewards(self: stormpy.models.SparseModel[ValueType]) → None

property SparsePomdp.reward_models

Reward models

SparsePomdp.set_initial_states(

self: stormpy.models.SparseModel[ValueType],

states: stormpy.datastructures.BitVector,

) → None

Set initial states

property SparsePomdp.state_valuations

state valuations

property SparsePomdp.states

Get states

property SparsePomdp.supports_parameters

Flag whether model supports parameters

property SparsePomdp.supports_uncertainty

Flag whether model supports uncertainty via intervals

SparsePomdp.to_dot(self: stormpy.models.SparseModel[ValueType]) → str

Write dot to a string

property SparsePomdp.transition_matrix

Transition matrix