Class sdm::PrivateHierarchicalOccupancyMDPWithHistory

Class List > sdm > PrivateHierarchicalOccupancyMDPWithHistory

#include <private_hierarchical_occupancy_mdp_with_history.hpp>

Inherits the following classes: sdm::PrivateHierarchicalOccupancyMDP

Public Attributes inherited from sdm::BaseOccupancyMDP

Type	Name
std::shared_ptr< HistoryInterface >	current_history_
std::shared_ptr< HistoryInterface >	initial_history_ Initial and current histories.

Public Attributes inherited from sdm::BaseBeliefMDP

See sdm::BaseBeliefMDP

Type	Name
int	batch_size_
std::shared_ptr< State >	current_state_ The current state (used in RL).
std::shared_ptr< Graph< std::shared_ptr< State >, Pair< std::shared_ptr< Action >, std::shared_ptr< Observation > > > >	mdp_graph_ the MDP __Graph (graph of state transition)
std::shared_ptr< Graph< double, Pair< std::shared_ptr< State >, std::shared_ptr< Action > > > >	reward_graph_
RecursiveMap< TBelief, std::shared_ptr< State > >	state_space_ A pointer on the bag containing all states.
int	step_ The current timestep (used in RL).
bool	store_actions_ = = true
bool	store_states_ = = true Hyperparameters.
RecursiveMap< std::shared_ptr< State >, std::shared_ptr< Action >, std::shared_ptr< Observation >, double >	transition_probability _The probability transition. (i.e. p(o

Public Static Attributes inherited from sdm::BaseOccupancyMDP

See sdm::BaseOccupancyMDP

Type	Name
unsigned long	MEAN_SIZE_STATE
number	PASSAGE_IN_NEXT_STATE
double	TIME_IN_APPLY_DR
double	TIME_IN_COMPRESS
double	TIME_IN_EXP_NEXT
double	TIME_IN_GET_ACTION
double	TIME_IN_GET_REWARD
double	TIME_IN_NEXT_OSTATE
double	TIME_IN_NEXT_STATE
double	TIME_IN_STEP
double	TIME_IN_UNDER_STEP

Public Functions

Type	Name
	PrivateHierarchicalOccupancyMDPWithHistory ()
	PrivateHierarchicalOccupancyMDPWithHistory (const std::shared_ptr< MPOMDPInterface > & dpomdp, number memory=-1, bool compression=true, bool store_states=true, bool store_actions=true, int batch_size=0)
virtual std::shared_ptr< Action >	getRandomAction (const std::shared_ptr< Observation > & observation, number t) Get random action.
virtual double	getReward (const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, number t=0) Get the expected reward of executing a specific action in a specific belief at timestep t.
virtual std::shared_ptr< Observation >	reset () Reset the environment and return initial observation.
virtual std::tuple< std::shared_ptr< Observation >, std::vector< double >, bool >	step (std::shared_ptr< Action > action) Do a step on the environment.

Public Functions inherited from sdm::PrivateHierarchicalOccupancyMDP

See sdm::PrivateHierarchicalOccupancyMDP

Type	Name
	PrivateHierarchicalOccupancyMDP ()
	PrivateHierarchicalOccupancyMDP (const std::shared_ptr< MPOMDPInterface > & dpomdp, number memory=-1, bool compression=true, bool store_states=true, bool store_actions=true, int batch_size=0)
virtual std::shared_ptr< Action >	applyDecisionRule (const std::shared_ptr< OccupancyStateInterface > & ostate, const std::shared_ptr< JointHistoryInterface > & joint_history, const std::shared_ptr< Action > & decision_rule, number t) const
virtual std::shared_ptr< Space >	computeActionSpaceAt (const std::shared_ptr< State > & occupancy_state, number t=0)
virtual std::shared_ptr< Action >	computeRandomAction (const std::shared_ptr< OccupancyStateInterface > & ostate, number t)
std::shared_ptr< State >	getJointHierarchicalLabels (const std::shared_ptr< State > & joint_labels, const std::shared_ptr< State > & ostate) const
virtual std::tuple< std::shared_ptr< Observation >, std::vector< double >, bool >	step (std::shared_ptr< Action > action) Do a step on the environment.

Public Functions inherited from sdm::BaseOccupancyMDP

See sdm::BaseOccupancyMDP

Type	Name
	BaseOccupancyMDP ()
	BaseOccupancyMDP (const std::shared_ptr< MPOMDPInterface > & dpomdp, number memory=-1, bool compression=true, bool store_states=true, bool store_actions=true, int batch_size=0)
virtual std::shared_ptr< Action >	applyDecisionRule (const std::shared_ptr< OccupancyStateInterface > & ostate, const std::shared_ptr< JointHistoryInterface > & joint_history, const std::shared_ptr< Action > & decision_rule, number t) const
virtual bool	checkCompatibility (const std::shared_ptr< Observation > & joint_observation, const std::shared_ptr< Observation > & observation)
virtual std::shared_ptr< Action >	computeRandomAction (const std::shared_ptr< OccupancyStateInterface > & ostate, number t)
virtual double	do_excess (double incumbent, double lb_value, double ub_value, double cost_so_far, double error, number t) Compute the excess of the HSVI paper. It refers to the termination condition.
virtual std::shared_ptr< Space >	getActionSpaceAt (const std::shared_ptr< State > & belief, number t=0) Get the action space at a specific belief and timestep.
virtual std::shared_ptr< Space >	getActionSpaceAt (const std::shared_ptr< Observation > & observation, number t=0) Get the action space.
virtual std::shared_ptr< Space >	getObservationSpaceAt (const std::shared_ptr< State > &, const std::shared_ptr< Action > &, number t) Get the observation space of the central planner.
virtual std::shared_ptr< Action >	getRandomAction (const std::shared_ptr< Observation > & observation, number t) Get random action.
virtual double	getReward (const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, number t=0) Get the expected reward of executing a specific action in a specific belief at timestep t.
double	getRewardBelief (const std::shared_ptr< BeliefInterface > & state, const std::shared_ptr< Action > & action, number t)
virtual std::shared_ptr< BeliefMDP >	getUnderlyingBeliefMDP () const Get the address of the underlying BeliefMDP.
virtual std::shared_ptr< MPOMDPInterface >	getUnderlyingMPOMDP () const Get the address of the underlying MPOMDP .
void	initialize (number memory)
virtual std::shared_ptr< State >	nextOccupancyState (const std::shared_ptr< State > & occupancy_state, const std::shared_ptr< Action > & decision_rule, const std::shared_ptr< Observation > & observation, number t=0) Get the next occupancy state.
virtual std::shared_ptr< Observation >	reset () Reset the environment and return initial observation.
virtual std::tuple< std::shared_ptr< Observation >, std::vector< double >, bool >	step (std::shared_ptr< Action > action) Do a step on the environment.
	~BaseOccupancyMDP ()

Public Functions inherited from sdm::BaseBeliefMDP

See sdm::BaseBeliefMDP

Type	Name
	BaseBeliefMDP ()
	BaseBeliefMDP (const std::shared_ptr< POMDPInterface > & pomdp, int batch_size=0)
virtual Pair< std::shared_ptr< State >, std::shared_ptr< State > >	computeExactNextState (const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t=0)
virtual std::shared_ptr< State >	computeNextState (const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t=0)
virtual Pair< std::shared_ptr< State >, double >	computeNextStateAndProbability (const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t=0) Compute the state transition in order to return next state and associated probability.
virtual Pair< std::shared_ptr< State >, std::shared_ptr< State > >	computeSampledNextState (const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t=0)
virtual std::shared_ptr< Space >	getActionSpaceAt (const std::shared_ptr< State > & belief, number t=0) Get the action space at a specific belief and timestep.
virtual std::shared_ptr< Space >	getActionSpaceAt (const std::shared_ptr< Observation > & observation, number t) Get the action space.
virtual double	getExpectedNextValue (const std::shared_ptr< ValueFunction > & value_function, const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, number t=0) Get the expected next value.
std::shared_ptr< Graph< std::shared_ptr< State >, Pair< std::shared_ptr< Action >, std::shared_ptr< Observation > > > >	getMDPGraph () Get the graph of.
virtual Pair< std::shared_ptr< State >, double >	getNextState (const std::shared_ptr< ValueFunction > & value_function, const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t)
virtual double	getObservationProbability (const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, const std::shared_ptr< State > & next_belief, const std::shared_ptr< Observation > & obs, number t=0) const Get the Observation _Probability p(o
virtual std::shared_ptr< Space >	getObservationSpaceAt (const std::shared_ptr< State > &, const std::shared_ptr< Action > &, number t)
virtual std::shared_ptr< Action >	getRandomAction (const std::shared_ptr< Observation > & observation, number t) Get random action.
virtual double	getReward (const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, number t=0) Get the expected reward of executing a specific action in a specific belief at timestep t.
std::vector< std::shared_ptr< State > >	getStoredStates () const
virtual std::shared_ptr< POMDPInterface >	getUnderlyingPOMDP () const Get the address of the underlying POMDP .
virtual std::shared_ptr< State >	nextBelief (const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t=0)
virtual Pair< std::shared_ptr< State >, double >	nextBeliefAndProba (const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t=0) Get the next belief.
virtual std::shared_ptr< State >	nextState (const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, number t=0, const std::shared_ptr< HSVI > & hsvi=nullptr) Select the next belief.
virtual std::shared_ptr< Observation >	reset () Reset the environment and return initial observation.
virtual std::tuple< std::shared_ptr< Observation >, std::vector< double >, bool >	step (std::shared_ptr< Action > action) Do a step on the environment.
	~BaseBeliefMDP ()

Public Functions inherited from sdm::SolvableByMDP

See sdm::SolvableByMDP

Type	Name
	SolvableByMDP () Default constructor.
	SolvableByMDP (const std::shared_ptr< MDPInterface > & mdp) Construct a problem solvable by HSVI .
virtual double	do_excess (double incumbent, double lb_value, double ub_value, double cost_so_far, double error, number horizon) Compute the excess of the HSVI paper. It refers to the termination condition.
virtual std::shared_ptr< Space >	getActionSpaceAt (const std::shared_ptr< State > & state, number t=0) Get the action space at a specific state and timestep. The state dependency is required when the game forbid the usage of a number of actions in this state. It is also used in some reformulated problems where actions are decision rules. The time dependency is required in extensive-form games in which some agents have a different action space.
virtual double	getDiscount (number t=0) const Get the specific discount factor for the problem at hand.
virtual double	getExpectedNextValue (const std::shared_ptr< ValueFunction > & value_function, const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t=0) Get the expected next value.
virtual std::shared_ptr< State >	getInitialState () Get the initial state.
virtual Pair< std::shared_ptr< State >, double >	getNextState (const std::shared_ptr< ValueFunction > & value_function, const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t)
virtual std::shared_ptr< Space >	getObservationSpaceAt (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t)
virtual double	getReward (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t=0) Get the reward of executing a specific action in an specific state at timestep t. The time dependency can be required in non-stationnary problems.
virtual const std::shared_ptr< MDPInterface > &	getUnderlyingProblem () const Get the well defined underlying problem. Some problems are solvable by DP algorithms even if they are not well defined. Usually, they simply are reformulation of an underlying well defined problem. For instance, the underlying DecPOMDP of the OccupancyMDP or the underlying POMDP of the current BeliefMDP.
virtual double	getWeightedDiscount (number t) Get the specific weighted discount factor for the problem at hand.
virtual bool	isSerialized () const Check if the problem is serialized.
virtual std::shared_ptr< State >	nextState (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t=0, const std::shared_ptr< HSVI > & hsvi=nullptr) Select the next state.
virtual Pair< std::shared_ptr< Action >, double >	selectNextAction (const std::shared_ptr< ValueFunction > & lb, const std::shared_ptr< ValueFunction > & ub, const std::shared_ptr< State > & s, number h) Select the next action.
virtual void	setInitialState (const std::shared_ptr< State > & state)

Public Functions inherited from sdm::SolvableByHSVI

See sdm::SolvableByHSVI

Type	Name
virtual double	do_excess (double incumbent, double lb_value, double ub_value, double cost_so_far, double error, number t) = 0 Compute the excess of the HSVI paper. It refers to the termination condition.
virtual std::shared_ptr< Space >	getActionSpaceAt (const std::shared_ptr< State > & state, number t) = 0 Get the action space at a specific state and timestep. The state dependency is required when the game forbid the usage of a number of actions in this state. It is also used in some reformulated problems where actions are decision rules. The time dependency is required in extensive-form games in which some agents have a different action space.
virtual double	getDiscount (number t) const = 0 Get the specific discount factor for the problem at hand.
virtual double	getExpectedNextValue (const std::shared_ptr< ValueFunction > & value_function, const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t) = 0 Get the expected next value.
virtual std::shared_ptr< State >	getInitialState () = 0 Get the initial state.
virtual Pair< std::shared_ptr< State >, double >	getNextState (const std::shared_ptr< ValueFunction > & value_function, const std::shared_ptr< State > & belief, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t) = 0
virtual std::shared_ptr< Space >	getObservationSpaceAt (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t) = 0
virtual double	getReward (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t) = 0 Get the reward of executing a specific action in an specific state at timestep t. The time dependency can be required in non-stationnary problems.
virtual const std::shared_ptr< MDPInterface > &	getUnderlyingProblem () const = 0 Get the well defined underlying problem. Some problems are solvable by DP algorithms even if they are not well defined. Usually, they simply are reformulation of an underlying well defined problem. For instance, the underlying DecPOMDP of the OccupancyMDP or the underlying POMDP of the current BeliefMDP.
virtual double	getWeightedDiscount (number t) = 0 Get the specific weighted discount factor for the problem at hand.
virtual bool	isSerialized () const = 0 Check if the problem is serialized.
virtual std::shared_ptr< State >	nextState (const std::shared_ptr< State > & state, const std::shared_ptr< Action > & action, number t=0, const std::shared_ptr< HSVI > & hsvi=nullptr) = 0 Select the next state.
virtual Pair< std::shared_ptr< Action >, double >	selectNextAction (const std::shared_ptr< ValueFunction > & lb, const std::shared_ptr< ValueFunction > & ub, const std::shared_ptr< State > & state, number t) = 0 Select the next action.
virtual void	setInitialState (const std::shared_ptr< State > &) = 0
virtual	~SolvableByHSVI ()

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 inherited from sdm::PrivateHierarchicalOccupancyMDP

See sdm::PrivateHierarchicalOccupancyMDP

Type	Name
std::shared_ptr< Action >	current_action_

Protected Attributes inherited from sdm::BaseOccupancyMDP

See sdm::BaseOccupancyMDP

Type	Name
std::shared_ptr< BeliefMDP >	belief_mdp_ Keep a pointer on the associated belief mdp that is used to compute next beliefs.
bool	compression_ = = true Hyperparameters.

Protected Attributes inherited from sdm::SolvableByMDP

See sdm::SolvableByMDP

Type	Name
std::shared_ptr< State >	initial_state_ The initial state.
std::shared_ptr< MDPInterface >	underlying_problem_ The underlying well defined problem.

Protected Functions

Type	Name
std::shared_ptr< HistoryInterface >	getJointLabel (const std::shared_ptr< HistoryInterface > & joint_history, const std::shared_ptr< State > & occupancy_state)

Protected Functions inherited from sdm::PrivateHierarchicalOccupancyMDP

See sdm::PrivateHierarchicalOccupancyMDP

Type	Name
virtual Pair< std::shared_ptr< State >, std::shared_ptr< State > >	computeExactNextState (const std::shared_ptr< State > & occupancy_state, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t=0)
virtual Pair< std::shared_ptr< State >, double >	computeNextStateAndProbability (const std::shared_ptr< State > & occupancy_state, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t=0) Compute the state transition in order to return next state and associated probability.
virtual Pair< std::shared_ptr< State >, std::shared_ptr< State > >	computeSampledNextState (const std::shared_ptr< State > & occupancy_state, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t=0)

Protected Functions inherited from sdm::BaseOccupancyMDP

See sdm::BaseOccupancyMDP

Type	Name
virtual std::shared_ptr< Space >	computeActionSpaceAt (const std::shared_ptr< State > & occupancy_state, number t=0)
virtual Pair< std::shared_ptr< State >, std::shared_ptr< State > >	computeExactNextState (const std::shared_ptr< State > & occupancy_state, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t=0)
virtual std::shared_ptr< State >	computeNextState (const std::shared_ptr< State > & occupancy_state, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t=0)
virtual Pair< std::shared_ptr< State >, double >	computeNextStateAndProbability (const std::shared_ptr< State > & occupancy_state, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t=0) Compute the state transition in order to return next state and associated probability.
virtual Pair< std::shared_ptr< State >, std::shared_ptr< State > >	computeSampledNextState (const std::shared_ptr< State > & occupancy_state, const std::shared_ptr< Action > & action, const std::shared_ptr< Observation > & observation, number t=0)
virtual bool	do_compression (number t) const Return true if compression must be done.
std::shared_ptr< HistoryInterface >	getNextHistory (const std::shared_ptr< Observation > & observation)
virtual void	update_occupancy_state_proba (const std::shared_ptr< OccupancyStateInterface > & occupancy_state, const std::shared_ptr< JointHistoryInterface > & joint_history, const std::shared_ptr< BeliefInterface > & belief, double probability)

Protected Functions inherited from sdm::SolvableByMDP

See sdm::SolvableByMDP

Type	Name
const std::shared_ptr< MDPInterface > &	getUnderlyingMDP () const Get the underlying mdp.

Public Functions Documentation

function PrivateHierarchicalOccupancyMDPWithHistory [1/2]

sdm::PrivateHierarchicalOccupancyMDPWithHistory::PrivateHierarchicalOccupancyMDPWithHistory ()

function PrivateHierarchicalOccupancyMDPWithHistory [2/2]

sdm::PrivateHierarchicalOccupancyMDPWithHistory::PrivateHierarchicalOccupancyMDPWithHistory (
    const std::shared_ptr< MPOMDPInterface > & dpomdp,
    number memory=-1,
    bool compression=true,
    bool store_states=true,
    bool store_actions=true,
    int batch_size=0
)

function getRandomAction

virtual std::shared_ptr< Action > sdm::PrivateHierarchicalOccupancyMDPWithHistory::getRandomAction (
    const std::shared_ptr< Observation > & observation,
    number t
)

Parameters:

observation the observation in consideration.
t time step.

Returns:

the random action.

Implements sdm::BaseOccupancyMDP::getRandomAction

function getReward

virtual double sdm::PrivateHierarchicalOccupancyMDPWithHistory::getReward (
    const std::shared_ptr< State > & belief,
    const std::shared_ptr< Action > & action,
    number t=0
)

Parameters:

belief the belief
action the action
t the timestep

Returns:

the reward

The time dependency can be required in non-stationnary problems.

Implements sdm::BaseOccupancyMDP::getReward

function reset

virtual std::shared_ptr< Observation > sdm::PrivateHierarchicalOccupancyMDPWithHistory::reset ()

Returns:

the initial observation

Implements sdm::BaseOccupancyMDP::reset

function step

virtual std::tuple< std::shared_ptr< Observation >, std::vector< double >, bool > sdm::PrivateHierarchicalOccupancyMDPWithHistory::step (
    std::shared_ptr< Action > action
)

Parameters:

action the action to execute

Returns:

the information produced. Include : next observation, rewards, episode done

Implements sdm::PrivateHierarchicalOccupancyMDP::step

Protected Functions Documentation

function getJointLabel

std::shared_ptr< HistoryInterface > sdm::PrivateHierarchicalOccupancyMDPWithHistory::getJointLabel (
    const std::shared_ptr< HistoryInterface > & joint_history,
    const std::shared_ptr< State > & occupancy_state
)

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