AIToolbox
A library that offers tools for AI problem solving.
MAUCEPolicy.hpp
Go to the documentation of this file.
1 #ifndef AI_TOOLBOX_FACTORED_BANDIT_MAUCE_POLICY_HEADER_FILE
2 #define AI_TOOLBOX_FACTORED_BANDIT_MAUCE_POLICY_HEADER_FILE
3 
9 
27  class MAUCEPolicy : public PolicyInterface {
28  public:
44  MAUCEPolicy(const Experience & exp, std::vector<double> ranges);
45 
59  virtual Action sampleAction() const override;
60 
71  virtual double getActionProbability(const Action & a) const override;
72 
82  const Experience & getExperience() const;
83 
84  private:
86  const Experience & exp_;
88  std::vector<double> rangesSquared_;
90  double logA_;
91  };
92 }
93 
94 #endif
AIToolbox::Factored::Bandit::MAUCEPolicy
This class represents the Multi-Agent Upper Confidence Exploration algorithm.
Definition: MAUCEPolicy.hpp:27
AIToolbox::Factored::Bandit::MAUCEPolicy::getActionProbability
virtual double getActionProbability(const Action &a) const override
This function returns the probability of taking the specified action.
Types.hpp
FilterMap.hpp
UCVE.hpp
AIToolbox::Factored::Bandit::Experience
This class computes averages and counts for a multi-agent cooperative Bandit problem.
Definition: Experience.hpp:14
PolicyInterface.hpp
AIToolbox::Factored::Bandit::MAUCEPolicy::getExperience
const Experience & getExperience() const
This function returns the RollingAverage learned from the data.
AIToolbox::Factored::Bandit::MAUCEPolicy::sampleAction
virtual Action sampleAction() const override
This function selects an action using MAUCE.
Experience.hpp
AIToolbox::Factored::Action
Factors Action
Definition: Types.hpp:69
AIToolbox::Factored::Bandit::PolicyInterface
Simple typedef for most of a normal Bandit's policy needs.
Definition: PolicyInterface.hpp:11
AIToolbox::Factored::Bandit::MAUCEPolicy::MAUCEPolicy
MAUCEPolicy(const Experience &exp, std::vector< double > ranges)
Basic constructor.
AIToolbox::Factored::Bandit
Definition: GraphUtils.hpp:12