Class sdm::SerializedMPOMDP

Class List > sdm > SerializedMPOMDP

• #include <serialized_mpomdp.hpp>

Inherits the following classes: sdm::SerialMPOMDPInterface, sdm::SerializedMMDP

Public Functions

Type	Name
	SerializedMPOMDP (std::shared_ptr< MPOMDPInterface > mpomdp)
virtual std::shared_ptr< Joint< std::shared_ptr< Observation > > >	getDefaultObservation () const
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 Get the Dynamics object.
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 Get the Obs Probability object.
virtual std::shared_ptr< Space >	getObservationSpace (number t) const Get the reachable next states.
virtual std::shared_ptr< Space >	getObservationSpace (number agent_id, number t) const Get ths observation space of agent i 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 the Reachablel Observations object.

Public Functions inherited from sdm::SerialMPOMDPInterface

See sdm::SerialMPOMDPInterface

Type	Name
virtual std::shared_ptr< Joint< std::shared_ptr< Observation > > >	getDefaultObservation () const = 0

Public Functions inherited from sdm::MMDPInterface

See sdm::MMDPInterface

Type	Name
virtual std::shared_ptr< Space >	getActionSpace (number agent_id, number t) const = 0 Get ths action space of agent i at timestep t.
virtual std::shared_ptr< Space >	getActionSpace (number t) const = 0 Get ths action space at timestep t.

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::SerialProblemInterface

See sdm::SerialProblemInterface

Type	Name
virtual number	getAgentId (number t) const = 0 Get the identifier of the current agent.
virtual bool	isLastAgent (number t) const = 0

Public Functions inherited from sdm::MPOMDPInterface

See sdm::MPOMDPInterface

Type	Name
virtual std::shared_ptr< Space >	getObservationSpace (number agent_id, number t) const = 0 Get ths observation space of agent i at timestep t.
virtual std::shared_ptr< Space >	getObservationSpace (number t) const = 0 Get ths observation space at timestep t.

Public Functions inherited from sdm::MMDPInterface

See sdm::MMDPInterface

Type	Name
virtual std::shared_ptr< Space >	getActionSpace (number agent_id, number t) const = 0 Get ths action space of agent i at timestep t.
virtual std::shared_ptr< Space >	getActionSpace (number t) const = 0 Get ths action space at timestep t.

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::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.

Public Functions inherited from sdm::SerializedMMDP

See sdm::SerializedMMDP

Type	Name
	SerializedMMDP (const std::shared_ptr< MMDPInterface > & mmdp)
virtual std::shared_ptr< Space >	getActionSpace (number t=0) const Get all actions at a specific time step.
virtual std::shared_ptr< Space >	getActionSpace (number agent_id, number t) const Get the Action Space at a specific time step and a precise agent.
virtual std::shared_ptr< Space >	getActionSpaceAt (const std::shared_ptr< Observation > & observation, number t) Get the action space.
virtual number	getAgentId (number t) const Get the identifier of the current agent.
virtual double	getDiscount (number t=0) const Get the discount factor at timestep t.
virtual number	getHorizon () const Get the number of agents.
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.
virtual std::shared_ptr< Distribution< std::shared_ptr< State > > >	getStartDistribution () const Get the initial distribution over states.
virtual std::shared_ptr< Space >	getStateSpace (number t=0) const Get all states.
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 bool	isLastAgent (number t) const
virtual std::shared_ptr< Observation >	reset () Reset the environment and return initial observation.
virtual void	setInternalState (std::shared_ptr< State > 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	~SerializedMMDP ()

Public Functions inherited from sdm::MMDPInterface

See sdm::MMDPInterface

Type	Name
virtual std::shared_ptr< Space >	getActionSpace (number agent_id, number t) const = 0 Get ths action space of agent i at timestep t.
virtual std::shared_ptr< Space >	getActionSpace (number t) const = 0 Get ths action space at timestep t.

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::SerialProblemInterface

See sdm::SerialProblemInterface

Type	Name
virtual number	getAgentId (number t) const = 0 Get the identifier of the current agent.
virtual bool	isLastAgent (number t) const = 0

Protected Attributes

Type	Name
std::shared_ptr< Observation >	empty_serial_observation
std::shared_ptr< ObservationDynamicsInterface >	obs_dynamics_ Map (serial state, seial action, serial observation, serial state) to Set of reachable seial observation.
Joint< std::shared_ptr< DiscreteSpace > >	serialized_observation_space_ Create the Observation __Space .

Protected Attributes inherited from sdm::SerializedMMDP

See sdm::SerializedMMDP

Type	Name
std::shared_ptr< Distribution< std::shared_ptr< State > > >	distribution_serial
std::unordered_map< Joint< std::shared_ptr< Action > >, std::shared_ptr< Action > >	map_joint_action_to_pointeur Map the joint_action to a precise pointeur of Action.
std::unordered_map< SerializedState, std::shared_ptr< State > >	map_serialized_state_to_pointeur Map the serialState to a precise pointeur of State .
std::shared_ptr< MMDPInterface >	mmdp_ The mmpdp associated to the problem.
Joint< std::shared_ptr< DiscreteSpace > >	serialized_state_space_ Refer to the Serialized State __Space .
std::shared_ptr< StateDynamicsInterface >	state_dynamics_ Map (serial state, seial action) to Set of reachable seial states.

Protected Functions

Type	Name
const std::shared_ptr< Observation >	getPointeurObservation (Joint< std::shared_ptr< Observation >> &) const Get the Pointeur object of a precise Joint Action.
void	setReachableObservationSpace (std::shared_ptr< MPOMDPInterface > mpomdp) Initialize "reachable_observation_space".
void	setupObservationSpace (std::shared_ptr< MPOMDPInterface > mpomdp) Initialize Serial Observation __Space .

Protected Functions inherited from sdm::SerializedMMDP

See sdm::SerializedMMDP

Type	Name
Joint< std::shared_ptr< Action > >	addNewAction (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & new_action) const A serial state is composed by a vector of action, in this function, we add a new action to the current vector of action/.
void	createDistribution ()
void	createInitReachableStateSpace () Initialize "serialized_state_space_".
void	createInitSerializedStateSpace () Initialize Serial State __Space .
const std::shared_ptr< Action >	getPointeurJointAction (Joint< std::shared_ptr< Action >> &) const Get the Pointeur object of a precise Joint Action.
const std::shared_ptr< State >	getPointeurState (SerializedState &) const Get the Pointeur object of a precise Joint Action.
void	setJointActionToPointeur (std::vector< Joint< std::shared_ptr< Action >>>)

Public Functions Documentation

function SerializedMPOMDP

sdm::SerializedMPOMDP::SerializedMPOMDP (
    std::shared_ptr< MPOMDPInterface > mpomdp
) 

function getDefaultObservation

virtual std::shared_ptr< Joint < std::shared_ptr< Observation > > > sdm::SerializedMPOMDP::getDefaultObservation () const

Implements sdm::SerialMPOMDPInterface::getDefaultObservation

function getDynamics

virtual double sdm::SerializedMPOMDP::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

Parameters:

• state
• action
• next_state
• observation
• t

Returns:

double

Implements sdm::POMDPInterface::getDynamics

function getObservationProbability

virtual double sdm::SerializedMPOMDP::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

Parameters:

• state
• action
• next_state
• observation
• t

Returns:

double

Implements sdm::POMDPInterface::getObservationProbability

function getObservationSpace [1/2]

virtual std::shared_ptr< Space > sdm::SerializedMPOMDP::getObservationSpace (
    number t
) const

Parameters:

• state the state
• action the action

Returns:

the set of reachable states

Implements sdm::MPOMDPInterface::getObservationSpace

function getObservationSpace [2/2]

virtual std::shared_ptr< Space > sdm::SerializedMPOMDP::getObservationSpace (
    number agent_id,
    number t
) const

Parameters:

• agent_id the identifier of the agent
• t the timestep

Returns:

the observation space

Implements sdm::MPOMDPInterface::getObservationSpace

function getReachableObservations

virtual std::set< std::shared_ptr< Observation > > sdm::SerializedMPOMDP::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
• action
• next_state
• t

Returns:

std::set<std::shared_ptr<Observation>>

Implements sdm::POMDPInterface::getReachableObservations

Protected Attributes Documentation

variable empty_serial_observation

std::shared_ptr<Observation> sdm::SerializedMPOMDP::empty_serial_observation;

variable obs_dynamics_

std::shared_ptr<ObservationDynamicsInterface> sdm::SerializedMPOMDP::obs_dynamics_;

variable serialized_observation_space_

Joint<std::shared_ptr<DiscreteSpace> > sdm::SerializedMPOMDP::serialized_observation_space_;

Protected Functions Documentation

function getPointeurObservation

const std::shared_ptr< Observation > sdm::SerializedMPOMDP::getPointeurObservation (
    Joint < std::shared_ptr< Observation >> &
) const

Returns:

std::shared_ptr<Joint<std::shared_ptr<Action>>>

function setReachableObservationSpace

void sdm::SerializedMPOMDP::setReachableObservationSpace (
    std::shared_ptr< MPOMDPInterface > mpomdp
) 

function setupObservationSpace

void sdm::SerializedMPOMDP::setupObservationSpace (
    std::shared_ptr< MPOMDPInterface > mpomdp
) 

---

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