SDM'Studio

Class sdm::POMDP

Class List > sdm > POMDP

The class for Discrete Partially Observable Markov Decision Processes.

  • #include <pomdp.hpp>

Inherits the following classes: sdm::MDP, sdm::POMDPInterface

Inherited by the following classes: sdm::MPOMDP

Public Functions

Type Name
POMDP ()
POMDP (const std::shared_ptr< Space > & state_space, const std::shared_ptr< Space > & action_space, const std::shared_ptr< Space > & obs_space, const std::shared_ptr< RewardInterface > & reward, const std::shared_ptr< StateDynamicsInterface > & state_dynamics, const std::shared_ptr< ObservationDynamicsInterface > & obs_dynamics, const std::shared_ptr< Distribution< std::shared_ptr< State >>> & start_distrib, number horizon=0, double discount=0.99, Criterion criterion=Criterion::REW_MAX)
virtual double getDynamics (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, const std::shared_ptr< State > & next_state, const std::shared_ptr< Observation > & observation, number t=0) const
_Get the dynamics, i.e. p(s', o
std::shared_ptr< ObservationDynamicsInterface > getObservationDynamics () const
virtual double getObservationProbability (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, const std::shared_ptr< State > & next_state, const std::shared_ptr< Observation > & observation, number t=0) const
_Get the observation probability, i.e. p(o
virtual std::shared_ptr< Space > getObservationSpace (number t=0) const
Get ths observation space at timestep t.
virtual std::set< std::shared_ptr< Observation > > getReachableObservations (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, const std::shared_ptr< State > & next_state, number t) const
Get reachable observations.
virtual std::shared_ptr< Observation > sampleNextObservation (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t)

Public Functions inherited from sdm::MDP

See sdm::MDP

Type Name
MDP ()
MDP (const std::shared_ptr< Space > & state_space, const std::shared_ptr< Space > & action_space, const std::shared_ptr< RewardInterface > & reward_space, const std::shared_ptr< StateDynamicsInterface > & state_dynamics, const std::shared_ptr< Distribution< std::shared_ptr< State >>> & start_distribution, number horizon=0, double discount=0.99, Criterion criterion=Criterion::REW_MAX)
void generateFile (std::string)
Save problem in file with given format (.xml, .json or .{dpomdp, posg, zsposg}).
virtual std::shared_ptr< Space > getActionSpace (number t=0) const
Get ths action space at timestep t.
virtual std::shared_ptr< Space > getActionSpaceAt (const std::shared_ptr< Observation > & observation, number t)
Get the action space.
virtual double getDiscount (number t=0) const
Get the discount factor at timestep t.
virtual number getHorizon () const
Get the planning horizon.
virtual std::shared_ptr< State > getInternalState () const
virtual double getMaxReward (number t=0) const
virtual double getMinReward (number t=0) const
virtual number getNumAgents () const
Get the number of agents.
virtual std::shared_ptr< Action > getRandomAction (const std::shared_ptr< Observation > & observation, number t)
Get random action.
virtual std::set< std::shared_ptr< State > > getReachableStates (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t=0) const
Get the reachable next states.
virtual double getReward (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t=0) const
Get the reward of executing action a in state s at timestep t.
virtual std::shared_ptr< RewardInterface > getRewardSpace () const
Get the reward function.
virtual std::shared_ptr< Distribution< std::shared_ptr< State > > > getStartDistribution () const
Get the initial distribution over states.
virtual std::shared_ptr< StateDynamicsInterface > getStateDynamics () const
Get the state dynamics.
virtual std::shared_ptr< Space > getStateSpace (number t=0) const
Get ths state space at timestep t.
virtual double getTransitionProbability (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, const std::shared_ptr< State > & next_state, number t=0) const
Get the Transition Probability object.
virtual std::shared_ptr< Observation > reset ()
Reset the environment and return initial observation.
virtual std::shared_ptr< Observation > sampleNextObservation (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t)
void setDiscount (double discount)
Set the discount factor.
void setHorizon (number horizon)
Set the planning horizon.
virtual void setInternalState (std::shared_ptr< State >)
virtual std::tuple< std::shared_ptr< Observation >, std::vector< double >, bool > step (std::shared_ptr< Action > action)
Do a step on the environment.
virtual std::tuple< std::shared_ptr< Observation >, std::vector< double >, bool > step (std::shared_ptr< Action > action, bool increment_timestep)
virtual std::string toJSON ()
Encodes MDP class into a string (JSON format).
virtual std::string toStdFormat ()
Encodes MDP class into a string (standard .posg or .dpomdp or .zsposg format).
virtual std::string toXML ()
Encodes MDP class into a string (XML format).
virtual ~MDP ()

Public Functions inherited from sdm::MDPInterface

See sdm::MDPInterface

Type Name
virtual std::shared_ptr< Space > getActionSpace (number t) const = 0
Get ths action space at timestep t.
virtual double getDiscount (number t) const = 0
Get the discount factor at timestep t.
virtual number getHorizon () const = 0
Get the number of agents.
virtual std::shared_ptr< State > getInternalState () const = 0
virtual double getMaxReward (number t) const = 0
virtual double getMinReward (number t) const = 0
virtual number getNumAgents () const = 0
Get the number of agents.
virtual std::set< std::shared_ptr< State > > getReachableStates (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t) const = 0
Get reachable states.
virtual double getReward (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t) const = 0
Get the reward at timestep t when executing an action in a specific state.
virtual std::shared_ptr< Distribution< std::shared_ptr< State > > > getStartDistribution () const = 0
Get the initial distribution over states.
virtual std::shared_ptr< Space > getStateSpace (number t) const = 0
Get ths state space at timestep t.
virtual double getTransitionProbability (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, const std::shared_ptr< State > & next_state, number t) const = 0
_Get the transition probability, i.e. p(s'
virtual void setInternalState (std::shared_ptr< State > state) = 0
virtual std::tuple< std::shared_ptr< Observation >, std::vector< double >, bool > step (std::shared_ptr< Action > action) = 0
Do a step on the environment.
virtual std::tuple< std::shared_ptr< Observation >, std::vector< double >, bool > step (std::shared_ptr< Action > action, bool increment_timestep) = 0

Public Functions inherited from sdm::GymInterface

See sdm::GymInterface

Type Name
virtual std::shared_ptr< Space > getActionSpaceAt (const std::shared_ptr< Observation > & observation, number t) = 0
Get the action space.
virtual std::shared_ptr< Action > getRandomAction (const std::shared_ptr< Observation > & observation, number t) = 0
Get random action.
virtual std::shared_ptr< Observation > reset () = 0
Reset the environment and return initial observation.
virtual std::tuple< std::shared_ptr< Observation >, std::vector< double >, bool > step (std::shared_ptr< Action > action) = 0
Do a step on the environment.

Public Functions inherited from sdm::GymInterface

See sdm::GymInterface

Type Name
virtual std::shared_ptr< Space > getActionSpaceAt (const std::shared_ptr< Observation > & observation, number t) = 0
Get the action space.
virtual std::shared_ptr< Action > getRandomAction (const std::shared_ptr< Observation > & observation, number t) = 0
Get random action.
virtual std::shared_ptr< Observation > reset () = 0
Reset the environment and return initial observation.
virtual std::tuple< std::shared_ptr< Observation >, std::vector< double >, bool > step (std::shared_ptr< Action > action) = 0
Do a step on the environment.

Public Functions inherited from sdm::POMDPInterface

See sdm::POMDPInterface

Type Name
virtual double getDynamics (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, const std::shared_ptr< State > & next_state, const std::shared_ptr< Observation > & observation, number t) const = 0
_Get the dynamics, i.e. p(s', o
virtual double getObservationProbability (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, const std::shared_ptr< State > & next_state, const std::shared_ptr< Observation > & observation, number t) const = 0
_Get the observation probability, i.e. p(o
virtual std::shared_ptr< Space > getObservationSpace (number t) const = 0
Get ths observation space at timestep t.
virtual std::set< std::shared_ptr< Observation > > getReachableObservations (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, const std::shared_ptr< State > & next_state, number t) const = 0
Get reachable observations.

Public Functions inherited from sdm::MDPInterface

See sdm::MDPInterface

Type Name
virtual std::shared_ptr< Space > getActionSpace (number t) const = 0
Get ths action space at timestep t.
virtual double getDiscount (number t) const = 0
Get the discount factor at timestep t.
virtual number getHorizon () const = 0
Get the number of agents.
virtual std::shared_ptr< State > getInternalState () const = 0
virtual double getMaxReward (number t) const = 0
virtual double getMinReward (number t) const = 0
virtual number getNumAgents () const = 0
Get the number of agents.
virtual std::set< std::shared_ptr< State > > getReachableStates (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t) const = 0
Get reachable states.
virtual double getReward (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t) const = 0
Get the reward at timestep t when executing an action in a specific state.
virtual std::shared_ptr< Distribution< std::shared_ptr< State > > > getStartDistribution () const = 0
Get the initial distribution over states.
virtual std::shared_ptr< Space > getStateSpace (number t) const = 0
Get ths state space at timestep t.
virtual double getTransitionProbability (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, const std::shared_ptr< State > & next_state, number t) const = 0
_Get the transition probability, i.e. p(s'
virtual void setInternalState (std::shared_ptr< State > state) = 0
virtual std::tuple< std::shared_ptr< Observation >, std::vector< double >, bool > step (std::shared_ptr< Action > action) = 0
Do a step on the environment.
virtual std::tuple< std::shared_ptr< Observation >, std::vector< double >, bool > step (std::shared_ptr< Action > action, bool increment_timestep) = 0

Public Functions inherited from sdm::GymInterface

See sdm::GymInterface

Type Name
virtual std::shared_ptr< Space > getActionSpaceAt (const std::shared_ptr< Observation > & observation, number t) = 0
Get the action space.
virtual std::shared_ptr< Action > getRandomAction (const std::shared_ptr< Observation > & observation, number t) = 0
Get random action.
virtual std::shared_ptr< Observation > reset () = 0
Reset the environment and return initial observation.
virtual std::tuple< std::shared_ptr< Observation >, std::vector< double >, bool > step (std::shared_ptr< Action > action) = 0
Do a step on the environment.

Protected Attributes

Type Name
std::shared_ptr< ObservationDynamicsInterface > observation_dynamics_
std::shared_ptr< Space > observation_space_

Protected Attributes inherited from sdm::MDP

See sdm::MDP

Type Name
std::shared_ptr< Space > action_space_
Criterion criterion_
int current_timestep_
double discount_
number horizon_
std::shared_ptr< State > internal_state_
number num_agents_
std::shared_ptr< RewardInterface > reward_space_
std::shared_ptr< Distribution< std::shared_ptr< State > > > start_distribution_
std::shared_ptr< StateDynamicsInterface > state_dynamics_
std::shared_ptr< Space > state_space_

Public Functions Documentation

function POMDP [1/2]

sdm::POMDP::POMDP ()

function POMDP [2/2]

sdm::POMDP::POMDP (
    const std::shared_ptr< Space > & state_space,
    const std::shared_ptr< Space > & action_space,
    const std::shared_ptr< Space > & obs_space,
    const std::shared_ptr< RewardInterface > & reward,
    const std::shared_ptr< StateDynamicsInterface > & state_dynamics,
    const std::shared_ptr< ObservationDynamicsInterface > & obs_dynamics,
    const std::shared_ptr< Distribution < std::shared_ptr< State >>> & start_distrib,
    number horizon=0,
    double discount=0.99,
    Criterion criterion=Criterion::REW_MAX
)

function getDynamics

virtual double sdm::POMDP::getDynamics (
    const std::shared_ptr< State > & state,
    const std::shared_ptr< Action > & action,
    const std::shared_ptr< State > & next_state,
    const std::shared_ptr< Observation > & observation,
    number t=0
) const

Parameters:

  • state the state at timestep t
  • action the action
  • next_state the next state, i.e. timestep t+1
  • observation the observation
  • t the timestep

Returns:

the probability

Implements sdm::POMDPInterface::getDynamics

function getObservationDynamics

std::shared_ptr< ObservationDynamicsInterface > sdm::POMDP::getObservationDynamics () const

function getObservationProbability

virtual double sdm::POMDP::getObservationProbability (
    const std::shared_ptr< State > & state,
    const std::shared_ptr< Action > & action,
    const std::shared_ptr< State > & next_state,
    const std::shared_ptr< Observation > & observation,
    number t=0
) const

Parameters:

  • action the action
  • next_state the next state
  • observation the observation
  • t the timestep

Returns:

the probability

Implements sdm::POMDPInterface::getObservationProbability

function getObservationSpace

virtual std::shared_ptr< Space > sdm::POMDP::getObservationSpace (
    number t=0
) const

Parameters:

  • t the timestep

Returns:

the observation space

Implements sdm::POMDPInterface::getObservationSpace

function getReachableObservations

virtual std::set< std::shared_ptr< Observation > > sdm::POMDP::getReachableObservations (
    const std::shared_ptr< State > & state,
    const std::shared_ptr< Action > & action,
    const std::shared_ptr< State > & next_state,
    number t
) const

Parameters:

  • state the current state
  • action the current action
  • next_state the next state

Returns:

the set of reachable observations

Implements sdm::POMDPInterface::getReachableObservations

function sampleNextObservation

virtual std::shared_ptr< Observation > sdm::POMDP::sampleNextObservation (
    const std::shared_ptr< State > & state,
    const std::shared_ptr< Action > & action,
    number t
)

Implements sdm::MDP::sampleNextObservation

Protected Attributes Documentation

variable observation_dynamics_

std::shared_ptr<ObservationDynamicsInterface> sdm::POMDP::observation_dynamics_;

variable observation_space_

std::shared_ptr<Space> sdm::POMDP::observation_space_;

The documentation for this class was generated from the following file src/sdm/world/pomdp.hpp